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": [
+    "q_proj",
+    "k_proj",
+    "out_proj",
+    "fc2",
+    "v_proj",
+    "fc1"
+  ],
+  "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:edbf7ef25965462786e086ff8722891d59b81b71df79f72058a133e61104dd36
+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-multirc-sequence_classification.json

@@ -0,0 +1,1158 @@
+{
+  "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": 12.125,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7155,
+      "step": 1
+    },
+    {
+      "epoch": 0.032,
+      "eval_exact_match": 0.02040816326530612,
+      "eval_f1_a": 0.5565749235474007,
+      "eval_f1_m": 0.33629307200735775,
+      "eval_loss": 0.7753984332084656,
+      "eval_runtime": 10.4348,
+      "eval_samples_per_second": 23.958,
+      "eval_steps_per_second": 3.067,
+      "step": 1
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 12.0,
+      "learning_rate": 5e-05,
+      "loss": 0.7399,
+      "step": 2
+    },
+    {
+      "epoch": 0.064,
+      "eval_exact_match": 0.04081632653061224,
+      "eval_f1_a": 0.5068493150684932,
+      "eval_f1_m": 0.35370757360553284,
+      "eval_loss": 0.7522656321525574,
+      "eval_runtime": 10.4218,
+      "eval_samples_per_second": 23.988,
+      "eval_steps_per_second": 3.07,
+      "step": 2
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 11.5,
+      "learning_rate": 4.9166666666666665e-05,
+      "loss": 0.8835,
+      "step": 3
+    },
+    {
+      "epoch": 0.096,
+      "eval_exact_match": 0.04081632653061224,
+      "eval_f1_a": 0.41702127659574467,
+      "eval_f1_m": 0.37501710307832775,
+      "eval_loss": 0.7389765381813049,
+      "eval_runtime": 10.4153,
+      "eval_samples_per_second": 24.003,
+      "eval_steps_per_second": 3.072,
+      "step": 3
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 14.4375,
+      "learning_rate": 4.8333333333333334e-05,
+      "loss": 0.7001,
+      "step": 4
+    },
+    {
+      "epoch": 0.128,
+      "eval_exact_match": 0.04081632653061224,
+      "eval_f1_a": 0.3893805309734513,
+      "eval_f1_m": 0.3756434608475426,
+      "eval_loss": 0.7378203272819519,
+      "eval_runtime": 10.419,
+      "eval_samples_per_second": 23.995,
+      "eval_steps_per_second": 3.071,
+      "step": 4
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 17.125,
+      "learning_rate": 4.75e-05,
+      "loss": 0.9135,
+      "step": 5
+    },
+    {
+      "epoch": 0.16,
+      "eval_exact_match": 0.04081632653061224,
+      "eval_f1_a": 0.3933054393305439,
+      "eval_f1_m": 0.3459301469505552,
+      "eval_loss": 0.7300781011581421,
+      "eval_runtime": 10.3243,
+      "eval_samples_per_second": 24.215,
+      "eval_steps_per_second": 3.099,
+      "step": 5
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 15.75,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.8408,
+      "step": 6
+    },
+    {
+      "epoch": 0.192,
+      "eval_exact_match": 0.04081632653061224,
+      "eval_f1_a": 0.424,
+      "eval_f1_m": 0.35033860697126,
+      "eval_loss": 0.7262031435966492,
+      "eval_runtime": 10.425,
+      "eval_samples_per_second": 23.981,
+      "eval_steps_per_second": 3.07,
+      "step": 6
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 5.75,
+      "learning_rate": 4.5833333333333334e-05,
+      "loss": 0.7823,
+      "step": 7
+    },
+    {
+      "epoch": 0.224,
+      "eval_exact_match": 0.02040816326530612,
+      "eval_f1_a": 0.43307086614173224,
+      "eval_f1_m": 0.3455767022093553,
+      "eval_loss": 0.7204062342643738,
+      "eval_runtime": 10.3184,
+      "eval_samples_per_second": 24.229,
+      "eval_steps_per_second": 3.101,
+      "step": 7
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 5.5,
+      "learning_rate": 4.5e-05,
+      "loss": 0.7459,
+      "step": 8
+    },
+    {
+      "epoch": 0.256,
+      "eval_exact_match": 0.02040816326530612,
+      "eval_f1_a": 0.4714828897338403,
+      "eval_f1_m": 0.35928306387490067,
+      "eval_loss": 0.7166640758514404,
+      "eval_runtime": 10.4237,
+      "eval_samples_per_second": 23.984,
+      "eval_steps_per_second": 3.07,
+      "step": 8
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 8.1875,
+      "learning_rate": 4.4166666666666665e-05,
+      "loss": 0.7278,
+      "step": 9
+    },
+    {
+      "epoch": 0.288,
+      "eval_exact_match": 0.02040816326530612,
+      "eval_f1_a": 0.46840148698884754,
+      "eval_f1_m": 0.3484207968901847,
+      "eval_loss": 0.7131797075271606,
+      "eval_runtime": 10.4331,
+      "eval_samples_per_second": 23.962,
+      "eval_steps_per_second": 3.067,
+      "step": 9
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 8.75,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.733,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "eval_exact_match": 0.12244897959183673,
+      "eval_f1_a": 0.3592814371257485,
+      "eval_f1_m": 0.46193067303511465,
+      "eval_loss": 0.7097499966621399,
+      "eval_runtime": 10.4174,
+      "eval_samples_per_second": 23.998,
+      "eval_steps_per_second": 3.072,
+      "step": 10
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 5.59375,
+      "learning_rate": 4.25e-05,
+      "loss": 0.7567,
+      "step": 11
+    },
+    {
+      "epoch": 0.352,
+      "eval_exact_match": 0.14285714285714285,
+      "eval_f1_a": 0.3712574850299401,
+      "eval_f1_m": 0.46697121072871356,
+      "eval_loss": 0.7058281302452087,
+      "eval_runtime": 10.4275,
+      "eval_samples_per_second": 23.975,
+      "eval_steps_per_second": 3.069,
+      "step": 11
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 12.0,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.6416,
+      "step": 12
+    },
+    {
+      "epoch": 0.384,
+      "eval_exact_match": 0.14285714285714285,
+      "eval_f1_a": 0.37267080745341613,
+      "eval_f1_m": 0.47003039644096056,
+      "eval_loss": 0.7006054520606995,
+      "eval_runtime": 10.4128,
+      "eval_samples_per_second": 24.009,
+      "eval_steps_per_second": 3.073,
+      "step": 12
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 4.40625,
+      "learning_rate": 4.0833333333333334e-05,
+      "loss": 0.7069,
+      "step": 13
+    },
+    {
+      "epoch": 0.416,
+      "eval_exact_match": 0.12244897959183673,
+      "eval_f1_a": 0.35220125786163525,
+      "eval_f1_m": 0.46111708752765157,
+      "eval_loss": 0.6990781426429749,
+      "eval_runtime": 10.3147,
+      "eval_samples_per_second": 24.237,
+      "eval_steps_per_second": 3.102,
+      "step": 13
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 7.65625,
+      "learning_rate": 4e-05,
+      "loss": 0.6904,
+      "step": 14
+    },
+    {
+      "epoch": 0.448,
+      "eval_exact_match": 0.12244897959183673,
+      "eval_f1_a": 0.3544303797468355,
+      "eval_f1_m": 0.46281776779976036,
+      "eval_loss": 0.6980976462364197,
+      "eval_runtime": 10.4232,
+      "eval_samples_per_second": 23.985,
+      "eval_steps_per_second": 3.07,
+      "step": 14
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 15.25,
+      "learning_rate": 3.9166666666666665e-05,
+      "loss": 0.6511,
+      "step": 15
+    },
+    {
+      "epoch": 0.48,
+      "eval_exact_match": 0.10204081632653061,
+      "eval_f1_a": 0.33986928104575165,
+      "eval_f1_m": 0.463017114937883,
+      "eval_loss": 0.6980116963386536,
+      "eval_runtime": 10.4242,
+      "eval_samples_per_second": 23.983,
+      "eval_steps_per_second": 3.07,
+      "step": 15
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 5.84375,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 0.6888,
+      "step": 16
+    },
+    {
+      "epoch": 0.512,
+      "eval_exact_match": 0.08163265306122448,
+      "eval_f1_a": 0.3194444444444445,
+      "eval_f1_m": 0.45772844102676014,
+      "eval_loss": 0.697152316570282,
+      "eval_runtime": 10.417,
+      "eval_samples_per_second": 23.999,
+      "eval_steps_per_second": 3.072,
+      "step": 16
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 5.78125,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.7102,
+      "step": 17
+    },
+    {
+      "epoch": 0.544,
+      "eval_exact_match": 0.08163265306122448,
+      "eval_f1_a": 0.31884057971014496,
+      "eval_f1_m": 0.4599919654841621,
+      "eval_loss": 0.7021523714065552,
+      "eval_runtime": 10.4225,
+      "eval_samples_per_second": 23.987,
+      "eval_steps_per_second": 3.07,
+      "step": 17
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 4.5,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.6583,
+      "step": 18
+    },
+    {
+      "epoch": 0.576,
+      "eval_exact_match": 0.061224489795918366,
+      "eval_f1_a": 0.2595419847328244,
+      "eval_f1_m": 0.4407286324453189,
+      "eval_loss": 0.709792971611023,
+      "eval_runtime": 10.4215,
+      "eval_samples_per_second": 23.989,
+      "eval_steps_per_second": 3.071,
+      "step": 18
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 5.25,
+      "learning_rate": 3.5833333333333335e-05,
+      "loss": 0.6852,
+      "step": 19
+    },
+    {
+      "epoch": 0.608,
+      "eval_exact_match": 0.04081632653061224,
+      "eval_f1_a": 0.1935483870967742,
+      "eval_f1_m": 0.4109555144068949,
+      "eval_loss": 0.729199230670929,
+      "eval_runtime": 10.3184,
+      "eval_samples_per_second": 24.228,
+      "eval_steps_per_second": 3.101,
+      "step": 19
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 8.4375,
+      "learning_rate": 3.5e-05,
+      "loss": 0.6293,
+      "step": 20
+    },
+    {
+      "epoch": 0.64,
+      "eval_exact_match": 0.04081632653061224,
+      "eval_f1_a": 0.13445378151260506,
+      "eval_f1_m": 0.38216542694333805,
+      "eval_loss": 0.7435839772224426,
+      "eval_runtime": 10.4133,
+      "eval_samples_per_second": 24.008,
+      "eval_steps_per_second": 3.073,
+      "step": 20
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 14.8125,
+      "learning_rate": 3.4166666666666666e-05,
+      "loss": 0.8031,
+      "step": 21
+    },
+    {
+      "epoch": 0.672,
+      "eval_exact_match": 0.04081632653061224,
+      "eval_f1_a": 0.13445378151260506,
+      "eval_f1_m": 0.38216542694333805,
+      "eval_loss": 0.7481308579444885,
+      "eval_runtime": 10.4163,
+      "eval_samples_per_second": 24.001,
+      "eval_steps_per_second": 3.072,
+      "step": 21
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 13.75,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.7602,
+      "step": 22
+    },
+    {
+      "epoch": 0.704,
+      "eval_exact_match": 0.061224489795918366,
+      "eval_f1_a": 0.13559322033898308,
+      "eval_f1_m": 0.3876076038140864,
+      "eval_loss": 0.7465839982032776,
+      "eval_runtime": 10.4283,
+      "eval_samples_per_second": 23.973,
+      "eval_steps_per_second": 3.069,
+      "step": 22
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 7.6875,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 0.6128,
+      "step": 23
+    },
+    {
+      "epoch": 0.736,
+      "eval_exact_match": 0.02040816326530612,
+      "eval_f1_a": 0.10344827586206896,
+      "eval_f1_m": 0.36175726367803196,
+      "eval_loss": 0.7520742416381836,
+      "eval_runtime": 10.4273,
+      "eval_samples_per_second": 23.975,
+      "eval_steps_per_second": 3.069,
+      "step": 23
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 4.90625,
+      "learning_rate": 3.1666666666666666e-05,
+      "loss": 0.722,
+      "step": 24
+    },
+    {
+      "epoch": 0.768,
+      "eval_exact_match": 0.02040816326530612,
+      "eval_f1_a": 0.08771929824561404,
+      "eval_f1_m": 0.3583559031338143,
+      "eval_loss": 0.7531718611717224,
+      "eval_runtime": 10.4184,
+      "eval_samples_per_second": 23.996,
+      "eval_steps_per_second": 3.071,
+      "step": 24
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 10.875,
+      "learning_rate": 3.0833333333333335e-05,
+      "loss": 0.7272,
+      "step": 25
+    },
+    {
+      "epoch": 0.8,
+      "eval_exact_match": 0.02040816326530612,
+      "eval_f1_a": 0.10344827586206896,
+      "eval_f1_m": 0.36175726367803196,
+      "eval_loss": 0.7432206869125366,
+      "eval_runtime": 10.4161,
+      "eval_samples_per_second": 24.001,
+      "eval_steps_per_second": 3.072,
+      "step": 25
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 5.46875,
+      "learning_rate": 3e-05,
+      "loss": 0.6684,
+      "step": 26
+    },
+    {
+      "epoch": 0.832,
+      "eval_exact_match": 0.04081632653061224,
+      "eval_f1_a": 0.10344827586206896,
+      "eval_f1_m": 0.3668593044943586,
+      "eval_loss": 0.7299179434776306,
+      "eval_runtime": 10.4124,
+      "eval_samples_per_second": 24.01,
+      "eval_steps_per_second": 3.073,
+      "step": 26
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 11.0625,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 0.5907,
+      "step": 27
+    },
+    {
+      "epoch": 0.864,
+      "eval_exact_match": 0.04081632653061224,
+      "eval_f1_a": 0.10434782608695652,
+      "eval_f1_m": 0.37196134531068514,
+      "eval_loss": 0.7278671860694885,
+      "eval_runtime": 10.4212,
+      "eval_samples_per_second": 23.99,
+      "eval_steps_per_second": 3.071,
+      "step": 27
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 8.0625,
+      "learning_rate": 2.8333333333333335e-05,
+      "loss": 0.7045,
+      "step": 28
+    },
+    {
+      "epoch": 0.896,
+      "eval_exact_match": 0.02040816326530612,
+      "eval_f1_a": 0.08928571428571429,
+      "eval_f1_m": 0.3716212092562633,
+      "eval_loss": 0.7314648628234863,
+      "eval_runtime": 10.2142,
+      "eval_samples_per_second": 24.476,
+      "eval_steps_per_second": 3.133,
+      "step": 28
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 5.4375,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 0.6714,
+      "step": 29
+    },
+    {
+      "epoch": 0.928,
+      "eval_exact_match": 0.0,
+      "eval_f1_a": 0.055045871559633024,
+      "eval_f1_m": 0.3568981771862925,
+      "eval_loss": 0.7325742244720459,
+      "eval_runtime": 10.3113,
+      "eval_samples_per_second": 24.245,
+      "eval_steps_per_second": 3.103,
+      "step": 29
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 14.625,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.8042,
+      "step": 30
+    },
+    {
+      "epoch": 0.96,
+      "eval_exact_match": 0.0,
+      "eval_f1_a": 0.055045871559633024,
+      "eval_f1_m": 0.3568981771862925,
+      "eval_loss": 0.7281132936477661,
+      "eval_runtime": 10.4268,
+      "eval_samples_per_second": 23.977,
+      "eval_steps_per_second": 3.069,
+      "step": 30
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 4.71875,
+      "learning_rate": 2.5833333333333336e-05,
+      "loss": 0.6815,
+      "step": 31
+    },
+    {
+      "epoch": 0.992,
+      "eval_exact_match": 0.02040816326530612,
+      "eval_f1_a": 0.08928571428571429,
+      "eval_f1_m": 0.3735648438529592,
+      "eval_loss": 0.7229745984077454,
+      "eval_runtime": 10.4294,
+      "eval_samples_per_second": 23.971,
+      "eval_steps_per_second": 3.068,
+      "step": 31
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 10.8125,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7198,
+      "step": 32
+    },
+    {
+      "epoch": 1.024,
+      "eval_exact_match": 0.04081632653061224,
+      "eval_f1_a": 0.11965811965811965,
+      "eval_f1_m": 0.3753627058549028,
+      "eval_loss": 0.7111640572547913,
+      "eval_runtime": 10.3253,
+      "eval_samples_per_second": 24.212,
+      "eval_steps_per_second": 3.099,
+      "step": 32
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 15.5,
+      "learning_rate": 2.4166666666666667e-05,
+      "loss": 0.7804,
+      "step": 33
+    },
+    {
+      "epoch": 1.056,
+      "eval_exact_match": 0.04081632653061224,
+      "eval_f1_a": 0.17886178861788618,
+      "eval_f1_m": 0.40101868253128753,
+      "eval_loss": 0.6996914148330688,
+      "eval_runtime": 10.8849,
+      "eval_samples_per_second": 22.968,
+      "eval_steps_per_second": 2.94,
+      "step": 33
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 5.96875,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.726,
+      "step": 34
+    },
+    {
+      "epoch": 1.088,
+      "eval_exact_match": 0.061224489795918366,
+      "eval_f1_a": 0.24806201550387594,
+      "eval_f1_m": 0.4362906667828635,
+      "eval_loss": 0.6891484260559082,
+      "eval_runtime": 10.415,
+      "eval_samples_per_second": 24.004,
+      "eval_steps_per_second": 3.073,
+      "step": 34
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 6.75,
+      "learning_rate": 2.25e-05,
+      "loss": 0.5805,
+      "step": 35
+    },
+    {
+      "epoch": 1.12,
+      "eval_exact_match": 0.10204081632653061,
+      "eval_f1_a": 0.2727272727272727,
+      "eval_f1_m": 0.4515967892318431,
+      "eval_loss": 0.6814296841621399,
+      "eval_runtime": 10.4242,
+      "eval_samples_per_second": 23.983,
+      "eval_steps_per_second": 3.07,
+      "step": 35
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 4.5,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 0.6754,
+      "step": 36
+    },
+    {
+      "epoch": 1.152,
+      "eval_exact_match": 0.10204081632653061,
+      "eval_f1_a": 0.2814814814814815,
+      "eval_f1_m": 0.4521069933134758,
+      "eval_loss": 0.6771992444992065,
+      "eval_runtime": 10.4266,
+      "eval_samples_per_second": 23.977,
+      "eval_steps_per_second": 3.069,
+      "step": 36
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 5.59375,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 0.7604,
+      "step": 37
+    },
+    {
+      "epoch": 1.184,
+      "eval_exact_match": 0.12244897959183673,
+      "eval_f1_a": 0.3216783216783217,
+      "eval_f1_m": 0.4626556283519067,
+      "eval_loss": 0.6751171946525574,
+      "eval_runtime": 10.4286,
+      "eval_samples_per_second": 23.972,
+      "eval_steps_per_second": 3.068,
+      "step": 37
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 4.46875,
+      "learning_rate": 2e-05,
+      "loss": 0.6905,
+      "step": 38
+    },
+    {
+      "epoch": 1.216,
+      "eval_exact_match": 0.12244897959183673,
+      "eval_f1_a": 0.33333333333333337,
+      "eval_f1_m": 0.4609179669203677,
+      "eval_loss": 0.674691379070282,
+      "eval_runtime": 10.4207,
+      "eval_samples_per_second": 23.991,
+      "eval_steps_per_second": 3.071,
+      "step": 38
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 7.8125,
+      "learning_rate": 1.9166666666666667e-05,
+      "loss": 0.7462,
+      "step": 39
+    },
+    {
+      "epoch": 1.248,
+      "eval_exact_match": 0.12244897959183673,
+      "eval_f1_a": 0.3875,
+      "eval_f1_m": 0.48344351393571067,
+      "eval_loss": 0.675179660320282,
+      "eval_runtime": 10.4254,
+      "eval_samples_per_second": 23.98,
+      "eval_steps_per_second": 3.069,
+      "step": 39
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 5.21875,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.6665,
+      "step": 40
+    },
+    {
+      "epoch": 1.28,
+      "eval_exact_match": 0.10204081632653061,
+      "eval_f1_a": 0.39024390243902435,
+      "eval_f1_m": 0.48039350272243414,
+      "eval_loss": 0.6755625009536743,
+      "eval_runtime": 10.4299,
+      "eval_samples_per_second": 23.97,
+      "eval_steps_per_second": 3.068,
+      "step": 40
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 6.78125,
+      "learning_rate": 1.75e-05,
+      "loss": 0.678,
+      "step": 41
+    },
+    {
+      "epoch": 1.312,
+      "eval_exact_match": 0.12244897959183673,
+      "eval_f1_a": 0.44692737430167595,
+      "eval_f1_m": 0.5051978933431513,
+      "eval_loss": 0.6769297122955322,
+      "eval_runtime": 10.4202,
+      "eval_samples_per_second": 23.992,
+      "eval_steps_per_second": 3.071,
+      "step": 41
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 9.0625,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.7455,
+      "step": 42
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "eval_exact_match": 0.12244897959183673,
+      "eval_f1_a": 0.45054945054945056,
+      "eval_f1_m": 0.5022014566732452,
+      "eval_loss": 0.6780156493186951,
+      "eval_runtime": 10.308,
+      "eval_samples_per_second": 24.253,
+      "eval_steps_per_second": 3.104,
+      "step": 42
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 8.125,
+      "learning_rate": 1.5833333333333333e-05,
+      "loss": 0.7665,
+      "step": 43
+    },
+    {
+      "epoch": 1.376,
+      "eval_exact_match": 0.12244897959183673,
+      "eval_f1_a": 0.44198895027624313,
+      "eval_f1_m": 0.4988324900389725,
+      "eval_loss": 0.6786093711853027,
+      "eval_runtime": 10.3137,
+      "eval_samples_per_second": 24.24,
+      "eval_steps_per_second": 3.103,
+      "step": 43
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 7.59375,
+      "learning_rate": 1.5e-05,
+      "loss": 0.7082,
+      "step": 44
+    },
+    {
+      "epoch": 1.408,
+      "eval_exact_match": 0.12244897959183673,
+      "eval_f1_a": 0.43956043956043955,
+      "eval_f1_m": 0.4970287382352207,
+      "eval_loss": 0.6788125038146973,
+      "eval_runtime": 10.4248,
+      "eval_samples_per_second": 23.981,
+      "eval_steps_per_second": 3.07,
+      "step": 44
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 8.625,
+      "learning_rate": 1.4166666666666668e-05,
+      "loss": 0.7339,
+      "step": 45
+    },
+    {
+      "epoch": 1.44,
+      "eval_exact_match": 0.12244897959183673,
+      "eval_f1_a": 0.4431818181818182,
+      "eval_f1_m": 0.5054916472083338,
+      "eval_loss": 0.6785781383514404,
+      "eval_runtime": 10.4273,
+      "eval_samples_per_second": 23.976,
+      "eval_steps_per_second": 3.069,
+      "step": 45
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 8.75,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7735,
+      "step": 46
+    },
+    {
+      "epoch": 1.472,
+      "eval_exact_match": 0.12244897959183673,
+      "eval_f1_a": 0.42603550295857984,
+      "eval_f1_m": 0.49595254685290685,
+      "eval_loss": 0.676101565361023,
+      "eval_runtime": 10.4169,
+      "eval_samples_per_second": 23.999,
+      "eval_steps_per_second": 3.072,
+      "step": 46
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 9.125,
+      "learning_rate": 1.25e-05,
+      "loss": 0.7253,
+      "step": 47
+    },
+    {
+      "epoch": 1.504,
+      "eval_exact_match": 0.12244897959183673,
+      "eval_f1_a": 0.4216867469879518,
+      "eval_f1_m": 0.49712994088744383,
+      "eval_loss": 0.676382839679718,
+      "eval_runtime": 10.4243,
+      "eval_samples_per_second": 23.983,
+      "eval_steps_per_second": 3.07,
+      "step": 47
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 5.5625,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.6836,
+      "step": 48
+    },
+    {
+      "epoch": 1.536,
+      "eval_exact_match": 0.12244897959183673,
+      "eval_f1_a": 0.3850931677018634,
+      "eval_f1_m": 0.4809896752573821,
+      "eval_loss": 0.6759296655654907,
+      "eval_runtime": 10.4271,
+      "eval_samples_per_second": 23.976,
+      "eval_steps_per_second": 3.069,
+      "step": 48
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 9.625,
+      "learning_rate": 1.0833333333333334e-05,
+      "loss": 0.7179,
+      "step": 49
+    },
+    {
+      "epoch": 1.568,
+      "eval_exact_match": 0.14285714285714285,
+      "eval_f1_a": 0.389937106918239,
+      "eval_f1_m": 0.48533855766748907,
+      "eval_loss": 0.6757344007492065,
+      "eval_runtime": 10.4218,
+      "eval_samples_per_second": 23.988,
+      "eval_steps_per_second": 3.07,
+      "step": 49
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 3.75,
+      "learning_rate": 1e-05,
+      "loss": 0.6541,
+      "step": 50
+    },
+    {
+      "epoch": 1.6,
+      "eval_exact_match": 0.14285714285714285,
+      "eval_f1_a": 0.3870967741935484,
+      "eval_f1_m": 0.4881032532893275,
+      "eval_loss": 0.675125002861023,
+      "eval_runtime": 10.4176,
+      "eval_samples_per_second": 23.998,
+      "eval_steps_per_second": 3.072,
+      "step": 50
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 16.375,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 0.6941,
+      "step": 51
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "eval_exact_match": 0.12244897959183673,
+      "eval_f1_a": 0.36486486486486486,
+      "eval_f1_m": 0.48323091474351965,
+      "eval_loss": 0.6745781302452087,
+      "eval_runtime": 10.4152,
+      "eval_samples_per_second": 24.003,
+      "eval_steps_per_second": 3.072,
+      "step": 51
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 11.8125,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.659,
+      "step": 52
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "eval_exact_match": 0.12244897959183673,
+      "eval_f1_a": 0.34965034965034963,
+      "eval_f1_m": 0.47547958910503907,
+      "eval_loss": 0.6751171946525574,
+      "eval_runtime": 10.412,
+      "eval_samples_per_second": 24.011,
+      "eval_steps_per_second": 3.073,
+      "step": 52
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 8.625,
+      "learning_rate": 7.5e-06,
+      "loss": 0.7233,
+      "step": 53
+    },
+    {
+      "epoch": 1.696,
+      "eval_exact_match": 0.12244897959183673,
+      "eval_f1_a": 0.3380281690140845,
+      "eval_f1_m": 0.46963543326088325,
+      "eval_loss": 0.674636721611023,
+      "eval_runtime": 10.4109,
+      "eval_samples_per_second": 24.013,
+      "eval_steps_per_second": 3.074,
+      "step": 53
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 4.84375,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.7446,
+      "step": 54
+    },
+    {
+      "epoch": 1.728,
+      "eval_exact_match": 0.10204081632653061,
+      "eval_f1_a": 0.3043478260869565,
+      "eval_f1_m": 0.45487667261376735,
+      "eval_loss": 0.676199197769165,
+      "eval_runtime": 10.4088,
+      "eval_samples_per_second": 24.018,
+      "eval_steps_per_second": 3.074,
+      "step": 54
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 7.5,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.6294,
+      "step": 55
+    },
+    {
+      "epoch": 1.76,
+      "eval_exact_match": 0.10204081632653061,
+      "eval_f1_a": 0.3043478260869565,
+      "eval_f1_m": 0.45487667261376735,
+      "eval_loss": 0.6773750185966492,
+      "eval_runtime": 10.4123,
+      "eval_samples_per_second": 24.01,
+      "eval_steps_per_second": 3.073,
+      "step": 55
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 10.375,
+      "learning_rate": 5e-06,
+      "loss": 0.6424,
+      "step": 56
+    },
+    {
+      "epoch": 1.792,
+      "eval_exact_match": 0.10204081632653061,
+      "eval_f1_a": 0.29411764705882354,
+      "eval_f1_m": 0.45487667261376735,
+      "eval_loss": 0.6775546669960022,
+      "eval_runtime": 10.4155,
+      "eval_samples_per_second": 24.003,
+      "eval_steps_per_second": 3.072,
+      "step": 56
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 7.34375,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.6522,
+      "step": 57
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "eval_exact_match": 0.10204081632653061,
+      "eval_f1_a": 0.29411764705882354,
+      "eval_f1_m": 0.45487667261376735,
+      "eval_loss": 0.6787461042404175,
+      "eval_runtime": 10.4149,
+      "eval_samples_per_second": 24.004,
+      "eval_steps_per_second": 3.073,
+      "step": 57
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 5.6875,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.6663,
+      "step": 58
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "eval_exact_match": 0.10204081632653061,
+      "eval_f1_a": 0.29411764705882354,
+      "eval_f1_m": 0.45487667261376735,
+      "eval_loss": 0.6782616972923279,
+      "eval_runtime": 10.4126,
+      "eval_samples_per_second": 24.009,
+      "eval_steps_per_second": 3.073,
+      "step": 58
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 10.1875,
+      "learning_rate": 2.5e-06,
+      "loss": 0.6491,
+      "step": 59
+    },
+    {
+      "epoch": 1.888,
+      "eval_exact_match": 0.10204081632653061,
+      "eval_f1_a": 0.29411764705882354,
+      "eval_f1_m": 0.45487667261376735,
+      "eval_loss": 0.6792226433753967,
+      "eval_runtime": 10.4178,
+      "eval_samples_per_second": 23.997,
+      "eval_steps_per_second": 3.072,
+      "step": 59
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 4.5625,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.6564,
+      "step": 60
+    },
+    {
+      "epoch": 1.92,
+      "eval_exact_match": 0.10204081632653061,
+      "eval_f1_a": 0.29411764705882354,
+      "eval_f1_m": 0.45487667261376735,
+      "eval_loss": 0.6789804697036743,
+      "eval_runtime": 10.4157,
+      "eval_samples_per_second": 24.002,
+      "eval_steps_per_second": 3.072,
+      "step": 60
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 9.375,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.5827,
+      "step": 61
+    },
+    {
+      "epoch": 1.952,
+      "eval_exact_match": 0.10204081632653061,
+      "eval_f1_a": 0.29411764705882354,
+      "eval_f1_m": 0.45487667261376735,
+      "eval_loss": 0.6795703172683716,
+      "eval_runtime": 10.4136,
+      "eval_samples_per_second": 24.007,
+      "eval_steps_per_second": 3.073,
+      "step": 61
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 10.5,
+      "learning_rate": 0.0,
+      "loss": 0.6918,
+      "step": 62
+    },
+    {
+      "epoch": 1.984,
+      "eval_exact_match": 0.10204081632653061,
+      "eval_f1_a": 0.29411764705882354,
+      "eval_f1_m": 0.45487667261376735,
+      "eval_loss": 0.6794179677963257,
+      "eval_runtime": 10.4107,
+      "eval_samples_per_second": 24.014,
+      "eval_steps_per_second": 3.074,
+      "step": 62
+    },
+    {
+      "epoch": 1.984,
+      "step": 62,
+      "total_flos": 3.579246979894477e+16,
+      "train_loss": 0.7075838888845136,
+      "train_runtime": 908.5635,
+      "train_samples_per_second": 2.201,
+      "train_steps_per_second": 0.068
+    }
+  ],
+  "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": 3.579246979894477e+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 sha256:910010bcfa9391154620b22b1e5ca4f5d164a907deb5c5905f4f6682a1a6fc37
+size 5176