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": [
+    "out_proj",
+    "k_proj",
+    "fc1",
+    "v_proj",
+    "q_proj",
+    "fc2"
+  ],
+  "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 sha256:835ab8a67021e87cd453433f34f63b3e54fb79dbe7b0d343915903b577d5315a
+size 37818360

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-boolq-sequence_classification.json

@@ -0,0 +1,1034 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.984,
+  "eval_steps": 1,
+  "global_step": 62,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032,
+      "grad_norm": 8.5625,
+      "learning_rate": 2.5e-05,
+      "loss": 0.733,
+      "step": 1
+    },
+    {
+      "epoch": 0.032,
+      "eval_accuracy": 0.6,
+      "eval_loss": 0.7043750286102295,
+      "eval_runtime": 5.8309,
+      "eval_samples_per_second": 42.875,
+      "eval_steps_per_second": 5.488,
+      "step": 1
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 8.3125,
+      "learning_rate": 5e-05,
+      "loss": 0.7766,
+      "step": 2
+    },
+    {
+      "epoch": 0.064,
+      "eval_accuracy": 0.58,
+      "eval_loss": 0.6986504197120667,
+      "eval_runtime": 5.9246,
+      "eval_samples_per_second": 42.197,
+      "eval_steps_per_second": 5.401,
+      "step": 2
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 8.75,
+      "learning_rate": 4.9166666666666665e-05,
+      "loss": 0.8106,
+      "step": 3
+    },
+    {
+      "epoch": 0.096,
+      "eval_accuracy": 0.588,
+      "eval_loss": 0.696652352809906,
+      "eval_runtime": 5.8737,
+      "eval_samples_per_second": 42.562,
+      "eval_steps_per_second": 5.448,
+      "step": 3
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 11.625,
+      "learning_rate": 4.8333333333333334e-05,
+      "loss": 0.8419,
+      "step": 4
+    },
+    {
+      "epoch": 0.128,
+      "eval_accuracy": 0.556,
+      "eval_loss": 0.7022871375083923,
+      "eval_runtime": 5.9244,
+      "eval_samples_per_second": 42.198,
+      "eval_steps_per_second": 5.401,
+      "step": 4
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 11.625,
+      "learning_rate": 4.75e-05,
+      "loss": 0.6818,
+      "step": 5
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.544,
+      "eval_loss": 0.7068164348602295,
+      "eval_runtime": 5.9214,
+      "eval_samples_per_second": 42.22,
+      "eval_steps_per_second": 5.404,
+      "step": 5
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 7.84375,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.6394,
+      "step": 6
+    },
+    {
+      "epoch": 0.192,
+      "eval_accuracy": 0.548,
+      "eval_loss": 0.7022500038146973,
+      "eval_runtime": 5.9245,
+      "eval_samples_per_second": 42.198,
+      "eval_steps_per_second": 5.401,
+      "step": 6
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 11.4375,
+      "learning_rate": 4.5833333333333334e-05,
+      "loss": 0.7657,
+      "step": 7
+    },
+    {
+      "epoch": 0.224,
+      "eval_accuracy": 0.552,
+      "eval_loss": 0.6960136890411377,
+      "eval_runtime": 5.9227,
+      "eval_samples_per_second": 42.21,
+      "eval_steps_per_second": 5.403,
+      "step": 7
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 11.4375,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6863,
+      "step": 8
+    },
+    {
+      "epoch": 0.256,
+      "eval_accuracy": 0.58,
+      "eval_loss": 0.6908359527587891,
+      "eval_runtime": 5.9191,
+      "eval_samples_per_second": 42.236,
+      "eval_steps_per_second": 5.406,
+      "step": 8
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 9.4375,
+      "learning_rate": 4.4166666666666665e-05,
+      "loss": 0.6082,
+      "step": 9
+    },
+    {
+      "epoch": 0.288,
+      "eval_accuracy": 0.584,
+      "eval_loss": 0.6917402148246765,
+      "eval_runtime": 5.9192,
+      "eval_samples_per_second": 42.235,
+      "eval_steps_per_second": 5.406,
+      "step": 9
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 13.125,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.7559,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "eval_accuracy": 0.604,
+      "eval_loss": 0.697378933429718,
+      "eval_runtime": 5.9209,
+      "eval_samples_per_second": 42.223,
+      "eval_steps_per_second": 5.405,
+      "step": 10
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 8.0,
+      "learning_rate": 4.25e-05,
+      "loss": 0.6119,
+      "step": 11
+    },
+    {
+      "epoch": 0.352,
+      "eval_accuracy": 0.608,
+      "eval_loss": 0.7080517411231995,
+      "eval_runtime": 5.9254,
+      "eval_samples_per_second": 42.192,
+      "eval_steps_per_second": 5.401,
+      "step": 11
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 7.5625,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.7329,
+      "step": 12
+    },
+    {
+      "epoch": 0.384,
+      "eval_accuracy": 0.608,
+      "eval_loss": 0.7140927910804749,
+      "eval_runtime": 5.9201,
+      "eval_samples_per_second": 42.229,
+      "eval_steps_per_second": 5.405,
+      "step": 12
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 12.3125,
+      "learning_rate": 4.0833333333333334e-05,
+      "loss": 0.5271,
+      "step": 13
+    },
+    {
+      "epoch": 0.416,
+      "eval_accuracy": 0.604,
+      "eval_loss": 0.7197051048278809,
+      "eval_runtime": 5.922,
+      "eval_samples_per_second": 42.216,
+      "eval_steps_per_second": 5.404,
+      "step": 13
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 5.875,
+      "learning_rate": 4e-05,
+      "loss": 0.7666,
+      "step": 14
+    },
+    {
+      "epoch": 0.448,
+      "eval_accuracy": 0.604,
+      "eval_loss": 0.7194697260856628,
+      "eval_runtime": 5.9186,
+      "eval_samples_per_second": 42.24,
+      "eval_steps_per_second": 5.407,
+      "step": 14
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 13.75,
+      "learning_rate": 3.9166666666666665e-05,
+      "loss": 0.7799,
+      "step": 15
+    },
+    {
+      "epoch": 0.48,
+      "eval_accuracy": 0.604,
+      "eval_loss": 0.7156533002853394,
+      "eval_runtime": 5.9165,
+      "eval_samples_per_second": 42.255,
+      "eval_steps_per_second": 5.409,
+      "step": 15
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 6.40625,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 0.6629,
+      "step": 16
+    },
+    {
+      "epoch": 0.512,
+      "eval_accuracy": 0.604,
+      "eval_loss": 0.7086992263793945,
+      "eval_runtime": 5.9244,
+      "eval_samples_per_second": 42.198,
+      "eval_steps_per_second": 5.401,
+      "step": 16
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 5.25,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.6303,
+      "step": 17
+    },
+    {
+      "epoch": 0.544,
+      "eval_accuracy": 0.608,
+      "eval_loss": 0.7018144726753235,
+      "eval_runtime": 5.9242,
+      "eval_samples_per_second": 42.2,
+      "eval_steps_per_second": 5.402,
+      "step": 17
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 14.25,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.9019,
+      "step": 18
+    },
+    {
+      "epoch": 0.576,
+      "eval_accuracy": 0.608,
+      "eval_loss": 0.6947382688522339,
+      "eval_runtime": 5.9231,
+      "eval_samples_per_second": 42.208,
+      "eval_steps_per_second": 5.403,
+      "step": 18
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 5.6875,
+      "learning_rate": 3.5833333333333335e-05,
+      "loss": 0.6538,
+      "step": 19
+    },
+    {
+      "epoch": 0.608,
+      "eval_accuracy": 0.6,
+      "eval_loss": 0.6891113519668579,
+      "eval_runtime": 5.9253,
+      "eval_samples_per_second": 42.192,
+      "eval_steps_per_second": 5.401,
+      "step": 19
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 6.90625,
+      "learning_rate": 3.5e-05,
+      "loss": 0.653,
+      "step": 20
+    },
+    {
+      "epoch": 0.64,
+      "eval_accuracy": 0.592,
+      "eval_loss": 0.6882695555686951,
+      "eval_runtime": 5.9204,
+      "eval_samples_per_second": 42.227,
+      "eval_steps_per_second": 5.405,
+      "step": 20
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 12.1875,
+      "learning_rate": 3.4166666666666666e-05,
+      "loss": 0.6106,
+      "step": 21
+    },
+    {
+      "epoch": 0.672,
+      "eval_accuracy": 0.592,
+      "eval_loss": 0.6871914267539978,
+      "eval_runtime": 5.9251,
+      "eval_samples_per_second": 42.194,
+      "eval_steps_per_second": 5.401,
+      "step": 21
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 7.28125,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.6786,
+      "step": 22
+    },
+    {
+      "epoch": 0.704,
+      "eval_accuracy": 0.592,
+      "eval_loss": 0.6855449080467224,
+      "eval_runtime": 5.9259,
+      "eval_samples_per_second": 42.187,
+      "eval_steps_per_second": 5.4,
+      "step": 22
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 6.875,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 0.6258,
+      "step": 23
+    },
+    {
+      "epoch": 0.736,
+      "eval_accuracy": 0.596,
+      "eval_loss": 0.6861640810966492,
+      "eval_runtime": 5.9226,
+      "eval_samples_per_second": 42.211,
+      "eval_steps_per_second": 5.403,
+      "step": 23
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 4.28125,
+      "learning_rate": 3.1666666666666666e-05,
+      "loss": 0.6652,
+      "step": 24
+    },
+    {
+      "epoch": 0.768,
+      "eval_accuracy": 0.596,
+      "eval_loss": 0.6845800876617432,
+      "eval_runtime": 5.9223,
+      "eval_samples_per_second": 42.214,
+      "eval_steps_per_second": 5.403,
+      "step": 24
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.84375,
+      "learning_rate": 3.0833333333333335e-05,
+      "loss": 0.6385,
+      "step": 25
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.584,
+      "eval_loss": 0.6855800747871399,
+      "eval_runtime": 5.9257,
+      "eval_samples_per_second": 42.189,
+      "eval_steps_per_second": 5.4,
+      "step": 25
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 7.28125,
+      "learning_rate": 3e-05,
+      "loss": 0.6714,
+      "step": 26
+    },
+    {
+      "epoch": 0.832,
+      "eval_accuracy": 0.588,
+      "eval_loss": 0.6856074333190918,
+      "eval_runtime": 5.9225,
+      "eval_samples_per_second": 42.212,
+      "eval_steps_per_second": 5.403,
+      "step": 26
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 8.0625,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 0.6958,
+      "step": 27
+    },
+    {
+      "epoch": 0.864,
+      "eval_accuracy": 0.584,
+      "eval_loss": 0.6856620907783508,
+      "eval_runtime": 5.9226,
+      "eval_samples_per_second": 42.211,
+      "eval_steps_per_second": 5.403,
+      "step": 27
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 9.375,
+      "learning_rate": 2.8333333333333335e-05,
+      "loss": 0.8685,
+      "step": 28
+    },
+    {
+      "epoch": 0.896,
+      "eval_accuracy": 0.588,
+      "eval_loss": 0.6862812638282776,
+      "eval_runtime": 5.9202,
+      "eval_samples_per_second": 42.228,
+      "eval_steps_per_second": 5.405,
+      "step": 28
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 9.5625,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 0.7247,
+      "step": 29
+    },
+    {
+      "epoch": 0.928,
+      "eval_accuracy": 0.592,
+      "eval_loss": 0.6854003667831421,
+      "eval_runtime": 5.9258,
+      "eval_samples_per_second": 42.188,
+      "eval_steps_per_second": 5.4,
+      "step": 29
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 5.96875,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.6199,
+      "step": 30
+    },
+    {
+      "epoch": 0.96,
+      "eval_accuracy": 0.592,
+      "eval_loss": 0.6848945021629333,
+      "eval_runtime": 5.9245,
+      "eval_samples_per_second": 42.197,
+      "eval_steps_per_second": 5.401,
+      "step": 30
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 5.34375,
+      "learning_rate": 2.5833333333333336e-05,
+      "loss": 0.6491,
+      "step": 31
+    },
+    {
+      "epoch": 0.992,
+      "eval_accuracy": 0.592,
+      "eval_loss": 0.6858437657356262,
+      "eval_runtime": 5.9198,
+      "eval_samples_per_second": 42.231,
+      "eval_steps_per_second": 5.406,
+      "step": 31
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 5.3125,
+      "learning_rate": 2.5e-05,
+      "loss": 0.6674,
+      "step": 32
+    },
+    {
+      "epoch": 1.024,
+      "eval_accuracy": 0.592,
+      "eval_loss": 0.6850195527076721,
+      "eval_runtime": 5.9233,
+      "eval_samples_per_second": 42.206,
+      "eval_steps_per_second": 5.402,
+      "step": 32
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 5.1875,
+      "learning_rate": 2.4166666666666667e-05,
+      "loss": 0.7468,
+      "step": 33
+    },
+    {
+      "epoch": 1.056,
+      "eval_accuracy": 0.596,
+      "eval_loss": 0.6846699118614197,
+      "eval_runtime": 5.928,
+      "eval_samples_per_second": 42.173,
+      "eval_steps_per_second": 5.398,
+      "step": 33
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 11.6875,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.7459,
+      "step": 34
+    },
+    {
+      "epoch": 1.088,
+      "eval_accuracy": 0.6,
+      "eval_loss": 0.6840722560882568,
+      "eval_runtime": 5.9285,
+      "eval_samples_per_second": 42.169,
+      "eval_steps_per_second": 5.398,
+      "step": 34
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 6.875,
+      "learning_rate": 2.25e-05,
+      "loss": 0.6869,
+      "step": 35
+    },
+    {
+      "epoch": 1.12,
+      "eval_accuracy": 0.596,
+      "eval_loss": 0.6836249828338623,
+      "eval_runtime": 5.9248,
+      "eval_samples_per_second": 42.195,
+      "eval_steps_per_second": 5.401,
+      "step": 35
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 4.6875,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 0.6937,
+      "step": 36
+    },
+    {
+      "epoch": 1.152,
+      "eval_accuracy": 0.592,
+      "eval_loss": 0.683789074420929,
+      "eval_runtime": 5.9264,
+      "eval_samples_per_second": 42.184,
+      "eval_steps_per_second": 5.4,
+      "step": 36
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 7.0625,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 0.6686,
+      "step": 37
+    },
+    {
+      "epoch": 1.184,
+      "eval_accuracy": 0.588,
+      "eval_loss": 0.684499979019165,
+      "eval_runtime": 5.9211,
+      "eval_samples_per_second": 42.222,
+      "eval_steps_per_second": 5.404,
+      "step": 37
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 7.15625,
+      "learning_rate": 2e-05,
+      "loss": 0.6833,
+      "step": 38
+    },
+    {
+      "epoch": 1.216,
+      "eval_accuracy": 0.584,
+      "eval_loss": 0.6837460994720459,
+      "eval_runtime": 5.9186,
+      "eval_samples_per_second": 42.24,
+      "eval_steps_per_second": 5.407,
+      "step": 38
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 3.890625,
+      "learning_rate": 1.9166666666666667e-05,
+      "loss": 0.7075,
+      "step": 39
+    },
+    {
+      "epoch": 1.248,
+      "eval_accuracy": 0.576,
+      "eval_loss": 0.6840898394584656,
+      "eval_runtime": 5.9275,
+      "eval_samples_per_second": 42.176,
+      "eval_steps_per_second": 5.399,
+      "step": 39
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 8.375,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.6724,
+      "step": 40
+    },
+    {
+      "epoch": 1.28,
+      "eval_accuracy": 0.568,
+      "eval_loss": 0.6857500076293945,
+      "eval_runtime": 5.9354,
+      "eval_samples_per_second": 42.12,
+      "eval_steps_per_second": 5.391,
+      "step": 40
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 12.0,
+      "learning_rate": 1.75e-05,
+      "loss": 0.7046,
+      "step": 41
+    },
+    {
+      "epoch": 1.312,
+      "eval_accuracy": 0.572,
+      "eval_loss": 0.6855937242507935,
+      "eval_runtime": 5.9205,
+      "eval_samples_per_second": 42.226,
+      "eval_steps_per_second": 5.405,
+      "step": 41
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 5.03125,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.6974,
+      "step": 42
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "eval_accuracy": 0.572,
+      "eval_loss": 0.6870351433753967,
+      "eval_runtime": 5.9614,
+      "eval_samples_per_second": 41.937,
+      "eval_steps_per_second": 5.368,
+      "step": 42
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 4.03125,
+      "learning_rate": 1.5833333333333333e-05,
+      "loss": 0.6517,
+      "step": 43
+    },
+    {
+      "epoch": 1.376,
+      "eval_accuracy": 0.572,
+      "eval_loss": 0.6863359212875366,
+      "eval_runtime": 6.1355,
+      "eval_samples_per_second": 40.747,
+      "eval_steps_per_second": 5.216,
+      "step": 43
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 11.875,
+      "learning_rate": 1.5e-05,
+      "loss": 0.6137,
+      "step": 44
+    },
+    {
+      "epoch": 1.408,
+      "eval_accuracy": 0.572,
+      "eval_loss": 0.6860390901565552,
+      "eval_runtime": 6.039,
+      "eval_samples_per_second": 41.398,
+      "eval_steps_per_second": 5.299,
+      "step": 44
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 7.3125,
+      "learning_rate": 1.4166666666666668e-05,
+      "loss": 0.6235,
+      "step": 45
+    },
+    {
+      "epoch": 1.44,
+      "eval_accuracy": 0.576,
+      "eval_loss": 0.6860234141349792,
+      "eval_runtime": 5.9313,
+      "eval_samples_per_second": 42.149,
+      "eval_steps_per_second": 5.395,
+      "step": 45
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 5.5,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.6591,
+      "step": 46
+    },
+    {
+      "epoch": 1.472,
+      "eval_accuracy": 0.572,
+      "eval_loss": 0.6854648590087891,
+      "eval_runtime": 5.9399,
+      "eval_samples_per_second": 42.088,
+      "eval_steps_per_second": 5.387,
+      "step": 46
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 4.65625,
+      "learning_rate": 1.25e-05,
+      "loss": 0.6518,
+      "step": 47
+    },
+    {
+      "epoch": 1.504,
+      "eval_accuracy": 0.572,
+      "eval_loss": 0.6862617135047913,
+      "eval_runtime": 5.9388,
+      "eval_samples_per_second": 42.096,
+      "eval_steps_per_second": 5.388,
+      "step": 47
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 5.875,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.7213,
+      "step": 48
+    },
+    {
+      "epoch": 1.536,
+      "eval_accuracy": 0.572,
+      "eval_loss": 0.6868203282356262,
+      "eval_runtime": 5.9401,
+      "eval_samples_per_second": 42.087,
+      "eval_steps_per_second": 5.387,
+      "step": 48
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 3.484375,
+      "learning_rate": 1.0833333333333334e-05,
+      "loss": 0.6219,
+      "step": 49
+    },
+    {
+      "epoch": 1.568,
+      "eval_accuracy": 0.572,
+      "eval_loss": 0.6863906383514404,
+      "eval_runtime": 5.9235,
+      "eval_samples_per_second": 42.205,
+      "eval_steps_per_second": 5.402,
+      "step": 49
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 11.25,
+      "learning_rate": 1e-05,
+      "loss": 0.6309,
+      "step": 50
+    },
+    {
+      "epoch": 1.6,
+      "eval_accuracy": 0.572,
+      "eval_loss": 0.6866523623466492,
+      "eval_runtime": 5.9289,
+      "eval_samples_per_second": 42.166,
+      "eval_steps_per_second": 5.397,
+      "step": 50
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 4.96875,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 0.6311,
+      "step": 51
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "eval_accuracy": 0.576,
+      "eval_loss": 0.6857929825782776,
+      "eval_runtime": 5.9373,
+      "eval_samples_per_second": 42.106,
+      "eval_steps_per_second": 5.39,
+      "step": 51
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 5.8125,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.7101,
+      "step": 52
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "eval_accuracy": 0.572,
+      "eval_loss": 0.6864804625511169,
+      "eval_runtime": 5.9361,
+      "eval_samples_per_second": 42.115,
+      "eval_steps_per_second": 5.391,
+      "step": 52
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 5.0,
+      "learning_rate": 7.5e-06,
+      "loss": 0.6605,
+      "step": 53
+    },
+    {
+      "epoch": 1.696,
+      "eval_accuracy": 0.568,
+      "eval_loss": 0.686718761920929,
+      "eval_runtime": 5.8868,
+      "eval_samples_per_second": 42.468,
+      "eval_steps_per_second": 5.436,
+      "step": 53
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 6.9375,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.7161,
+      "step": 54
+    },
+    {
+      "epoch": 1.728,
+      "eval_accuracy": 0.572,
+      "eval_loss": 0.6871640682220459,
+      "eval_runtime": 5.8848,
+      "eval_samples_per_second": 42.482,
+      "eval_steps_per_second": 5.438,
+      "step": 54
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 5.4375,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.7532,
+      "step": 55
+    },
+    {
+      "epoch": 1.76,
+      "eval_accuracy": 0.572,
+      "eval_loss": 0.6864922046661377,
+      "eval_runtime": 5.9431,
+      "eval_samples_per_second": 42.065,
+      "eval_steps_per_second": 5.384,
+      "step": 55
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 4.8125,
+      "learning_rate": 5e-06,
+      "loss": 0.7025,
+      "step": 56
+    },
+    {
+      "epoch": 1.792,
+      "eval_accuracy": 0.572,
+      "eval_loss": 0.6855624914169312,
+      "eval_runtime": 5.9353,
+      "eval_samples_per_second": 42.121,
+      "eval_steps_per_second": 5.391,
+      "step": 56
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 9.0625,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.631,
+      "step": 57
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "eval_accuracy": 0.572,
+      "eval_loss": 0.6870039105415344,
+      "eval_runtime": 5.8895,
+      "eval_samples_per_second": 42.448,
+      "eval_steps_per_second": 5.433,
+      "step": 57
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 5.46875,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.6203,
+      "step": 58
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "eval_accuracy": 0.572,
+      "eval_loss": 0.6862148642539978,
+      "eval_runtime": 5.9398,
+      "eval_samples_per_second": 42.089,
+      "eval_steps_per_second": 5.387,
+      "step": 58
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 4.53125,
+      "learning_rate": 2.5e-06,
+      "loss": 0.6924,
+      "step": 59
+    },
+    {
+      "epoch": 1.888,
+      "eval_accuracy": 0.572,
+      "eval_loss": 0.6864296793937683,
+      "eval_runtime": 5.9454,
+      "eval_samples_per_second": 42.049,
+      "eval_steps_per_second": 5.382,
+      "step": 59
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 7.59375,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.7316,
+      "step": 60
+    },
+    {
+      "epoch": 1.92,
+      "eval_accuracy": 0.576,
+      "eval_loss": 0.6849257946014404,
+      "eval_runtime": 5.9302,
+      "eval_samples_per_second": 42.157,
+      "eval_steps_per_second": 5.396,
+      "step": 60
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 7.125,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.6077,
+      "step": 61
+    },
+    {
+      "epoch": 1.952,
+      "eval_accuracy": 0.572,
+      "eval_loss": 0.6858437657356262,
+      "eval_runtime": 5.9452,
+      "eval_samples_per_second": 42.051,
+      "eval_steps_per_second": 5.383,
+      "step": 61
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 9.625,
+      "learning_rate": 0.0,
+      "loss": 0.5587,
+      "step": 62
+    },
+    {
+      "epoch": 1.984,
+      "eval_accuracy": 0.576,
+      "eval_loss": 0.6857460737228394,
+      "eval_runtime": 5.9442,
+      "eval_samples_per_second": 42.058,
+      "eval_steps_per_second": 5.383,
+      "step": 62
+    },
+    {
+      "epoch": 1.984,
+      "step": 62,
+      "total_flos": 1.3708912637247488e+16,
+      "train_loss": 0.6859967631678427,
+      "train_runtime": 502.3798,
+      "train_samples_per_second": 3.981,
+      "train_steps_per_second": 0.123
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 62,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 1.3708912637247488e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b84ed2b7d9974ccc63d7d44db770d0621cb29ab73239696a86c5929826f285
+size 5176