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": [
+    "k_proj",
+    "fc1",
+    "v_proj",
+    "q_proj",
+    "out_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:bde51f7f5ee4c14b8d0f86c53da7a718395f6c5fb8852b97acc18db73a9b762c
+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-wic-sequence_classification.json

@@ -0,0 +1,1002 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.6,
+  "eval_steps": 1,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 10.0,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7248,
+      "step": 1
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.504,
+      "eval_loss": 0.7169140577316284,
+      "eval_runtime": 1.7694,
+      "eval_samples_per_second": 141.288,
+      "eval_steps_per_second": 3.956,
+      "step": 1
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 11.3125,
+      "learning_rate": 5e-05,
+      "loss": 0.7141,
+      "step": 2
+    },
+    {
+      "epoch": 0.32,
+      "eval_accuracy": 0.512,
+      "eval_loss": 0.713210940361023,
+      "eval_runtime": 1.908,
+      "eval_samples_per_second": 131.027,
+      "eval_steps_per_second": 3.669,
+      "step": 2
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 8.5,
+      "learning_rate": 4.913793103448276e-05,
+      "loss": 0.72,
+      "step": 3
+    },
+    {
+      "epoch": 0.48,
+      "eval_accuracy": 0.516,
+      "eval_loss": 0.7183730602264404,
+      "eval_runtime": 1.9102,
+      "eval_samples_per_second": 130.879,
+      "eval_steps_per_second": 3.665,
+      "step": 3
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 9.1875,
+      "learning_rate": 4.827586206896552e-05,
+      "loss": 0.7007,
+      "step": 4
+    },
+    {
+      "epoch": 0.64,
+      "eval_accuracy": 0.516,
+      "eval_loss": 0.7356113195419312,
+      "eval_runtime": 1.908,
+      "eval_samples_per_second": 131.029,
+      "eval_steps_per_second": 3.669,
+      "step": 4
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 9.4375,
+      "learning_rate": 4.741379310344828e-05,
+      "loss": 0.8173,
+      "step": 5
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.516,
+      "eval_loss": 0.7247294783592224,
+      "eval_runtime": 1.9079,
+      "eval_samples_per_second": 131.036,
+      "eval_steps_per_second": 3.669,
+      "step": 5
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 10.6875,
+      "learning_rate": 4.655172413793104e-05,
+      "loss": 0.716,
+      "step": 6
+    },
+    {
+      "epoch": 0.96,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.7145995497703552,
+      "eval_runtime": 1.906,
+      "eval_samples_per_second": 131.162,
+      "eval_steps_per_second": 3.673,
+      "step": 6
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 3.15625,
+      "learning_rate": 4.5689655172413794e-05,
+      "loss": 0.7381,
+      "step": 7
+    },
+    {
+      "epoch": 1.12,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.7026171684265137,
+      "eval_runtime": 1.9082,
+      "eval_samples_per_second": 131.015,
+      "eval_steps_per_second": 3.668,
+      "step": 7
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 3.0625,
+      "learning_rate": 4.482758620689655e-05,
+      "loss": 0.6973,
+      "step": 8
+    },
+    {
+      "epoch": 1.28,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6966249942779541,
+      "eval_runtime": 1.9071,
+      "eval_samples_per_second": 131.086,
+      "eval_steps_per_second": 3.67,
+      "step": 8
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.2734375,
+      "learning_rate": 4.396551724137931e-05,
+      "loss": 0.6871,
+      "step": 9
+    },
+    {
+      "epoch": 1.44,
+      "eval_accuracy": 0.516,
+      "eval_loss": 0.6961289048194885,
+      "eval_runtime": 1.9103,
+      "eval_samples_per_second": 130.872,
+      "eval_steps_per_second": 3.664,
+      "step": 9
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 4.21875,
+      "learning_rate": 4.3103448275862066e-05,
+      "loss": 0.6943,
+      "step": 10
+    },
+    {
+      "epoch": 1.6,
+      "eval_accuracy": 0.508,
+      "eval_loss": 0.6979374885559082,
+      "eval_runtime": 1.9058,
+      "eval_samples_per_second": 131.178,
+      "eval_steps_per_second": 3.673,
+      "step": 10
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.8671875,
+      "learning_rate": 4.224137931034483e-05,
+      "loss": 0.7017,
+      "step": 11
+    },
+    {
+      "epoch": 1.76,
+      "eval_accuracy": 0.508,
+      "eval_loss": 0.6969297528266907,
+      "eval_runtime": 1.9056,
+      "eval_samples_per_second": 131.193,
+      "eval_steps_per_second": 3.673,
+      "step": 11
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 6.28125,
+      "learning_rate": 4.1379310344827587e-05,
+      "loss": 0.6898,
+      "step": 12
+    },
+    {
+      "epoch": 1.92,
+      "eval_accuracy": 0.512,
+      "eval_loss": 0.6961719393730164,
+      "eval_runtime": 1.9059,
+      "eval_samples_per_second": 131.172,
+      "eval_steps_per_second": 3.673,
+      "step": 12
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 2.75,
+      "learning_rate": 4.0517241379310344e-05,
+      "loss": 0.6945,
+      "step": 13
+    },
+    {
+      "epoch": 2.08,
+      "eval_accuracy": 0.508,
+      "eval_loss": 0.6973124742507935,
+      "eval_runtime": 1.9053,
+      "eval_samples_per_second": 131.212,
+      "eval_steps_per_second": 3.674,
+      "step": 13
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 1.4765625,
+      "learning_rate": 3.965517241379311e-05,
+      "loss": 0.713,
+      "step": 14
+    },
+    {
+      "epoch": 2.24,
+      "eval_accuracy": 0.512,
+      "eval_loss": 0.6960234642028809,
+      "eval_runtime": 1.9114,
+      "eval_samples_per_second": 130.792,
+      "eval_steps_per_second": 3.662,
+      "step": 14
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.1171875,
+      "learning_rate": 3.8793103448275865e-05,
+      "loss": 0.682,
+      "step": 15
+    },
+    {
+      "epoch": 2.4,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6956601738929749,
+      "eval_runtime": 1.9077,
+      "eval_samples_per_second": 131.049,
+      "eval_steps_per_second": 3.669,
+      "step": 15
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.2734375,
+      "learning_rate": 3.793103448275862e-05,
+      "loss": 0.68,
+      "step": 16
+    },
+    {
+      "epoch": 2.56,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6956210732460022,
+      "eval_runtime": 1.9087,
+      "eval_samples_per_second": 130.982,
+      "eval_steps_per_second": 3.668,
+      "step": 16
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 4.5625,
+      "learning_rate": 3.7068965517241385e-05,
+      "loss": 0.6793,
+      "step": 17
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6956055164337158,
+      "eval_runtime": 1.9077,
+      "eval_samples_per_second": 131.05,
+      "eval_steps_per_second": 3.669,
+      "step": 17
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 2.15625,
+      "learning_rate": 3.620689655172414e-05,
+      "loss": 0.6879,
+      "step": 18
+    },
+    {
+      "epoch": 2.88,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6959649324417114,
+      "eval_runtime": 1.9058,
+      "eval_samples_per_second": 131.178,
+      "eval_steps_per_second": 3.673,
+      "step": 18
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 2.796875,
+      "learning_rate": 3.53448275862069e-05,
+      "loss": 0.6963,
+      "step": 19
+    },
+    {
+      "epoch": 3.04,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.697027325630188,
+      "eval_runtime": 1.8566,
+      "eval_samples_per_second": 134.654,
+      "eval_steps_per_second": 3.77,
+      "step": 19
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 5.3125,
+      "learning_rate": 3.4482758620689657e-05,
+      "loss": 0.6925,
+      "step": 20
+    },
+    {
+      "epoch": 3.2,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6985077857971191,
+      "eval_runtime": 1.9069,
+      "eval_samples_per_second": 131.1,
+      "eval_steps_per_second": 3.671,
+      "step": 20
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 2.984375,
+      "learning_rate": 3.3620689655172414e-05,
+      "loss": 0.6911,
+      "step": 21
+    },
+    {
+      "epoch": 3.36,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.699636697769165,
+      "eval_runtime": 1.859,
+      "eval_samples_per_second": 134.479,
+      "eval_steps_per_second": 3.765,
+      "step": 21
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 3.59375,
+      "learning_rate": 3.275862068965517e-05,
+      "loss": 0.6882,
+      "step": 22
+    },
+    {
+      "epoch": 3.52,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.7012538909912109,
+      "eval_runtime": 1.9094,
+      "eval_samples_per_second": 130.928,
+      "eval_steps_per_second": 3.666,
+      "step": 22
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 3.875,
+      "learning_rate": 3.1896551724137935e-05,
+      "loss": 0.7016,
+      "step": 23
+    },
+    {
+      "epoch": 3.68,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.7007499933242798,
+      "eval_runtime": 1.9071,
+      "eval_samples_per_second": 131.091,
+      "eval_steps_per_second": 3.671,
+      "step": 23
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 5.46875,
+      "learning_rate": 3.103448275862069e-05,
+      "loss": 0.6972,
+      "step": 24
+    },
+    {
+      "epoch": 3.84,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.7000390887260437,
+      "eval_runtime": 1.9058,
+      "eval_samples_per_second": 131.18,
+      "eval_steps_per_second": 3.673,
+      "step": 24
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.125,
+      "learning_rate": 3.017241379310345e-05,
+      "loss": 0.7288,
+      "step": 25
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.697628915309906,
+      "eval_runtime": 1.9065,
+      "eval_samples_per_second": 131.13,
+      "eval_steps_per_second": 3.672,
+      "step": 25
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 1.9765625,
+      "learning_rate": 2.9310344827586206e-05,
+      "loss": 0.7239,
+      "step": 26
+    },
+    {
+      "epoch": 4.16,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6958945393562317,
+      "eval_runtime": 1.9088,
+      "eval_samples_per_second": 130.974,
+      "eval_steps_per_second": 3.667,
+      "step": 26
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 7.125,
+      "learning_rate": 2.844827586206897e-05,
+      "loss": 0.6701,
+      "step": 27
+    },
+    {
+      "epoch": 4.32,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6942812204360962,
+      "eval_runtime": 1.9094,
+      "eval_samples_per_second": 130.934,
+      "eval_steps_per_second": 3.666,
+      "step": 27
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 1.484375,
+      "learning_rate": 2.7586206896551727e-05,
+      "loss": 0.7093,
+      "step": 28
+    },
+    {
+      "epoch": 4.48,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6918594241142273,
+      "eval_runtime": 1.9103,
+      "eval_samples_per_second": 130.869,
+      "eval_steps_per_second": 3.664,
+      "step": 28
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 5.0,
+      "learning_rate": 2.672413793103448e-05,
+      "loss": 0.6803,
+      "step": 29
+    },
+    {
+      "epoch": 4.64,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6925703287124634,
+      "eval_runtime": 1.9097,
+      "eval_samples_per_second": 130.908,
+      "eval_steps_per_second": 3.665,
+      "step": 29
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.91015625,
+      "learning_rate": 2.5862068965517244e-05,
+      "loss": 0.6953,
+      "step": 30
+    },
+    {
+      "epoch": 4.8,
+      "eval_accuracy": 0.516,
+      "eval_loss": 0.6929374933242798,
+      "eval_runtime": 1.9088,
+      "eval_samples_per_second": 130.971,
+      "eval_steps_per_second": 3.667,
+      "step": 30
+    },
+    {
+      "epoch": 4.96,
+      "grad_norm": 4.1875,
+      "learning_rate": 2.5e-05,
+      "loss": 0.6946,
+      "step": 31
+    },
+    {
+      "epoch": 4.96,
+      "eval_accuracy": 0.508,
+      "eval_loss": 0.6934375166893005,
+      "eval_runtime": 1.908,
+      "eval_samples_per_second": 131.026,
+      "eval_steps_per_second": 3.669,
+      "step": 31
+    },
+    {
+      "epoch": 5.12,
+      "grad_norm": 1.40625,
+      "learning_rate": 2.413793103448276e-05,
+      "loss": 0.7016,
+      "step": 32
+    },
+    {
+      "epoch": 5.12,
+      "eval_accuracy": 0.504,
+      "eval_loss": 0.6947265863418579,
+      "eval_runtime": 1.9084,
+      "eval_samples_per_second": 131.001,
+      "eval_steps_per_second": 3.668,
+      "step": 32
+    },
+    {
+      "epoch": 5.28,
+      "grad_norm": 3.03125,
+      "learning_rate": 2.327586206896552e-05,
+      "loss": 0.6953,
+      "step": 33
+    },
+    {
+      "epoch": 5.28,
+      "eval_accuracy": 0.504,
+      "eval_loss": 0.6949218511581421,
+      "eval_runtime": 1.9078,
+      "eval_samples_per_second": 131.039,
+      "eval_steps_per_second": 3.669,
+      "step": 33
+    },
+    {
+      "epoch": 5.44,
+      "grad_norm": 1.4609375,
+      "learning_rate": 2.2413793103448276e-05,
+      "loss": 0.6936,
+      "step": 34
+    },
+    {
+      "epoch": 5.44,
+      "eval_accuracy": 0.504,
+      "eval_loss": 0.6933984160423279,
+      "eval_runtime": 1.9062,
+      "eval_samples_per_second": 131.154,
+      "eval_steps_per_second": 3.672,
+      "step": 34
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 4.21875,
+      "learning_rate": 2.1551724137931033e-05,
+      "loss": 0.6759,
+      "step": 35
+    },
+    {
+      "epoch": 5.6,
+      "eval_accuracy": 0.512,
+      "eval_loss": 0.6927656531333923,
+      "eval_runtime": 1.9079,
+      "eval_samples_per_second": 131.032,
+      "eval_steps_per_second": 3.669,
+      "step": 35
+    },
+    {
+      "epoch": 5.76,
+      "grad_norm": 3.890625,
+      "learning_rate": 2.0689655172413793e-05,
+      "loss": 0.6911,
+      "step": 36
+    },
+    {
+      "epoch": 5.76,
+      "eval_accuracy": 0.516,
+      "eval_loss": 0.691476583480835,
+      "eval_runtime": 1.9084,
+      "eval_samples_per_second": 131.001,
+      "eval_steps_per_second": 3.668,
+      "step": 36
+    },
+    {
+      "epoch": 5.92,
+      "grad_norm": 3.921875,
+      "learning_rate": 1.9827586206896554e-05,
+      "loss": 0.7045,
+      "step": 37
+    },
+    {
+      "epoch": 5.92,
+      "eval_accuracy": 0.516,
+      "eval_loss": 0.6917109489440918,
+      "eval_runtime": 1.9104,
+      "eval_samples_per_second": 130.863,
+      "eval_steps_per_second": 3.664,
+      "step": 37
+    },
+    {
+      "epoch": 6.08,
+      "grad_norm": 6.53125,
+      "learning_rate": 1.896551724137931e-05,
+      "loss": 0.6951,
+      "step": 38
+    },
+    {
+      "epoch": 6.08,
+      "eval_accuracy": 0.516,
+      "eval_loss": 0.6929374933242798,
+      "eval_runtime": 1.9058,
+      "eval_samples_per_second": 131.178,
+      "eval_steps_per_second": 3.673,
+      "step": 38
+    },
+    {
+      "epoch": 6.24,
+      "grad_norm": 3.671875,
+      "learning_rate": 1.810344827586207e-05,
+      "loss": 0.6766,
+      "step": 39
+    },
+    {
+      "epoch": 6.24,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6927499771118164,
+      "eval_runtime": 1.908,
+      "eval_samples_per_second": 131.03,
+      "eval_steps_per_second": 3.669,
+      "step": 39
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 2.421875,
+      "learning_rate": 1.7241379310344828e-05,
+      "loss": 0.6964,
+      "step": 40
+    },
+    {
+      "epoch": 6.4,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.693472683429718,
+      "eval_runtime": 1.9083,
+      "eval_samples_per_second": 131.006,
+      "eval_steps_per_second": 3.668,
+      "step": 40
+    },
+    {
+      "epoch": 6.5600000000000005,
+      "grad_norm": 0.9765625,
+      "learning_rate": 1.6379310344827585e-05,
+      "loss": 0.6899,
+      "step": 41
+    },
+    {
+      "epoch": 6.5600000000000005,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.69287109375,
+      "eval_runtime": 1.9071,
+      "eval_samples_per_second": 131.089,
+      "eval_steps_per_second": 3.67,
+      "step": 41
+    },
+    {
+      "epoch": 6.72,
+      "grad_norm": 3.21875,
+      "learning_rate": 1.5517241379310346e-05,
+      "loss": 0.6783,
+      "step": 42
+    },
+    {
+      "epoch": 6.72,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6933398246765137,
+      "eval_runtime": 1.9073,
+      "eval_samples_per_second": 131.076,
+      "eval_steps_per_second": 3.67,
+      "step": 42
+    },
+    {
+      "epoch": 6.88,
+      "grad_norm": 0.87890625,
+      "learning_rate": 1.4655172413793103e-05,
+      "loss": 0.6921,
+      "step": 43
+    },
+    {
+      "epoch": 6.88,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6933085918426514,
+      "eval_runtime": 1.9103,
+      "eval_samples_per_second": 130.87,
+      "eval_steps_per_second": 3.664,
+      "step": 43
+    },
+    {
+      "epoch": 7.04,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.3793103448275863e-05,
+      "loss": 0.684,
+      "step": 44
+    },
+    {
+      "epoch": 7.04,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6930469274520874,
+      "eval_runtime": 1.9088,
+      "eval_samples_per_second": 130.974,
+      "eval_steps_per_second": 3.667,
+      "step": 44
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 6.3125,
+      "learning_rate": 1.2931034482758622e-05,
+      "loss": 0.7027,
+      "step": 45
+    },
+    {
+      "epoch": 7.2,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6939062476158142,
+      "eval_runtime": 1.909,
+      "eval_samples_per_second": 130.958,
+      "eval_steps_per_second": 3.667,
+      "step": 45
+    },
+    {
+      "epoch": 7.36,
+      "grad_norm": 3.78125,
+      "learning_rate": 1.206896551724138e-05,
+      "loss": 0.6893,
+      "step": 46
+    },
+    {
+      "epoch": 7.36,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6937148571014404,
+      "eval_runtime": 1.9058,
+      "eval_samples_per_second": 131.178,
+      "eval_steps_per_second": 3.673,
+      "step": 46
+    },
+    {
+      "epoch": 7.52,
+      "grad_norm": 3.4375,
+      "learning_rate": 1.1206896551724138e-05,
+      "loss": 0.6754,
+      "step": 47
+    },
+    {
+      "epoch": 7.52,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6943007707595825,
+      "eval_runtime": 1.8591,
+      "eval_samples_per_second": 134.472,
+      "eval_steps_per_second": 3.765,
+      "step": 47
+    },
+    {
+      "epoch": 7.68,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.0344827586206897e-05,
+      "loss": 0.7103,
+      "step": 48
+    },
+    {
+      "epoch": 7.68,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6930898427963257,
+      "eval_runtime": 1.9082,
+      "eval_samples_per_second": 131.014,
+      "eval_steps_per_second": 3.668,
+      "step": 48
+    },
+    {
+      "epoch": 7.84,
+      "grad_norm": 6.0625,
+      "learning_rate": 9.482758620689655e-06,
+      "loss": 0.6965,
+      "step": 49
+    },
+    {
+      "epoch": 7.84,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6940312385559082,
+      "eval_runtime": 1.9059,
+      "eval_samples_per_second": 131.173,
+      "eval_steps_per_second": 3.673,
+      "step": 49
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 5.46875,
+      "learning_rate": 8.620689655172414e-06,
+      "loss": 0.682,
+      "step": 50
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6938086152076721,
+      "eval_runtime": 1.9046,
+      "eval_samples_per_second": 131.261,
+      "eval_steps_per_second": 3.675,
+      "step": 50
+    },
+    {
+      "epoch": 8.16,
+      "grad_norm": 2.15625,
+      "learning_rate": 7.758620689655173e-06,
+      "loss": 0.6914,
+      "step": 51
+    },
+    {
+      "epoch": 8.16,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6924687623977661,
+      "eval_runtime": 1.9055,
+      "eval_samples_per_second": 131.197,
+      "eval_steps_per_second": 3.674,
+      "step": 51
+    },
+    {
+      "epoch": 8.32,
+      "grad_norm": 4.09375,
+      "learning_rate": 6.896551724137932e-06,
+      "loss": 0.6963,
+      "step": 52
+    },
+    {
+      "epoch": 8.32,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6934570074081421,
+      "eval_runtime": 1.9059,
+      "eval_samples_per_second": 131.17,
+      "eval_steps_per_second": 3.673,
+      "step": 52
+    },
+    {
+      "epoch": 8.48,
+      "grad_norm": 1.2265625,
+      "learning_rate": 6.03448275862069e-06,
+      "loss": 0.6962,
+      "step": 53
+    },
+    {
+      "epoch": 8.48,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6923359632492065,
+      "eval_runtime": 1.9059,
+      "eval_samples_per_second": 131.173,
+      "eval_steps_per_second": 3.673,
+      "step": 53
+    },
+    {
+      "epoch": 8.64,
+      "grad_norm": 3.578125,
+      "learning_rate": 5.172413793103448e-06,
+      "loss": 0.6692,
+      "step": 54
+    },
+    {
+      "epoch": 8.64,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6927656531333923,
+      "eval_runtime": 1.906,
+      "eval_samples_per_second": 131.168,
+      "eval_steps_per_second": 3.673,
+      "step": 54
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 1.7421875,
+      "learning_rate": 4.310344827586207e-06,
+      "loss": 0.6991,
+      "step": 55
+    },
+    {
+      "epoch": 8.8,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6923280954360962,
+      "eval_runtime": 1.9063,
+      "eval_samples_per_second": 131.146,
+      "eval_steps_per_second": 3.672,
+      "step": 55
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 1.1796875,
+      "learning_rate": 3.448275862068966e-06,
+      "loss": 0.6808,
+      "step": 56
+    },
+    {
+      "epoch": 8.96,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.692800760269165,
+      "eval_runtime": 1.9066,
+      "eval_samples_per_second": 131.124,
+      "eval_steps_per_second": 3.671,
+      "step": 56
+    },
+    {
+      "epoch": 9.12,
+      "grad_norm": 9.25,
+      "learning_rate": 2.586206896551724e-06,
+      "loss": 0.7043,
+      "step": 57
+    },
+    {
+      "epoch": 9.12,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6924726366996765,
+      "eval_runtime": 1.9066,
+      "eval_samples_per_second": 131.123,
+      "eval_steps_per_second": 3.671,
+      "step": 57
+    },
+    {
+      "epoch": 9.28,
+      "grad_norm": 1.15625,
+      "learning_rate": 1.724137931034483e-06,
+      "loss": 0.6786,
+      "step": 58
+    },
+    {
+      "epoch": 9.28,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6920429468154907,
+      "eval_runtime": 1.9069,
+      "eval_samples_per_second": 131.104,
+      "eval_steps_per_second": 3.671,
+      "step": 58
+    },
+    {
+      "epoch": 9.44,
+      "grad_norm": 6.125,
+      "learning_rate": 8.620689655172415e-07,
+      "loss": 0.6852,
+      "step": 59
+    },
+    {
+      "epoch": 9.44,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6916835904121399,
+      "eval_runtime": 1.9088,
+      "eval_samples_per_second": 130.97,
+      "eval_steps_per_second": 3.667,
+      "step": 59
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 1.3828125,
+      "learning_rate": 0.0,
+      "loss": 0.6888,
+      "step": 60
+    },
+    {
+      "epoch": 9.6,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6920117139816284,
+      "eval_runtime": 1.9079,
+      "eval_samples_per_second": 131.035,
+      "eval_steps_per_second": 3.669,
+      "step": 60
+    },
+    {
+      "epoch": 9.6,
+      "step": 60,
+      "total_flos": 2.337091978736435e+16,
+      "train_loss": 0.6971277634302775,
+      "train_runtime": 291.0168,
+      "train_samples_per_second": 34.362,
+      "train_steps_per_second": 0.206
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 60,
+  "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": 2.337091978736435e+16,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68472283c67ba76a2e2a15e33d92f180feafc6ff186bb481f424d2d65a117a63
+size 5112