Model save

README.md

@@ -1,281 +1,132 @@
 ---
-language: en
-license: mit
-model_details: "\n        ## Abstract\n        This model, 'distilbert-finetuned-uncased',\
-  \ is a question-answering chatbot trained on the SQuAD dataset, demonstrating competency\
-  \ in building conversational AI using recent advances in natural language processing.\
-  \ It utilizes a BERT model fine-tuned for extractive question answering.\n\n   \
-  \     ## Data Collection and Preprocessing\n        The model was trained on the\
-  \ Stanford Question Answering Dataset (SQuAD), which contains over 100,000 question-answer\
-  \ pairs based on Wikipedia articles. The data preprocessing involved tokenizing\
-  \ context paragraphs and questions, truncating sequences to fit BERT's max length,\
-  \ and adding special tokens to mark question and paragraph segments.\n\n       \
-  \ ## Model Architecture and Training\n        The architecture is based on the BERT\
-  \ transformer model, which was pretrained on large unlabeled text corpora. For this\
-  \ project, the BERT base model was fine-tuned on SQuAD for extractive question answering,\
-  \ with additional output layers for predicting the start and end indices of the\
-  \ answer span.\n\n        ## SQuAD 2.0 Dataset\n        SQuAD 2.0 combines the existing\
-  \ SQuAD data with over 50,000 unanswerable questions written adversarially by crowdworkers\
-  \ to look similar to answerable ones. This version of the dataset challenges models\
-  \ to not only produce answers when possible but also determine when no answer is\
-  \ supported by the paragraph and abstain from answering.\n        "
-intended_use: "\n        - Answering questions from the squad_v2 dataset.\n      \
-  \  - Developing question-answering systems within the scope of the aai520-project.\n\
-  \        - Research and experimentation in the NLP question-answering domain.\n\
-  \        "
-limitations_and_bias: "\n        The model inherits limitations and biases from the\
-  \ 'distilbert-base-uncased' model, as it was trained on the same foundational data.\n\
-  \        It may underperform on questions that are ambiguous or too far outside\
-  \ the scope of the topics covered in the squad_v2 dataset.\n        Additionally,\
-  \ the model may reflect societal biases present in its training data.\n        "
-ethical_considerations: "\n        This model should not be used for making critical\
-  \ decisions without human oversight,\n        as it can generate incorrect or biased\
-  \ answers, especially for topics not covered in the training data.\n        Users\
-  \ should also consider the ethical implications of using AI in decision-making processes\
-  \ and the potential for perpetuating biases.\n        "
-evaluation: "\n        The model was evaluated on the squad_v2 dataset using various\
-  \ metrics. These metrics, along with their corresponding scores,\n        are detailed\
-  \ in the 'eval_results' section. The evaluation process ensured a comprehensive\
-  \ assessment of the model's performance\n        in question-answering scenarios.\n\
-  \        "
-training: "\n        The model was trained over 10 epochs with a learning rate of\
-  \ 2e-05, using a batch size of 128.\n        The training utilized a cross-entropy\
-  \ loss function and the AdamW optimizer, with gradient accumulation over 4 steps.\n\
-  \        "
-tips_and_tricks: "\n        For optimal performance, questions should be clear, concise,\
-  \ and grammatically correct.\n        The model performs best on questions related\
-  \ to topics covered in the squad_v2 dataset.\n        It is advisable to pre-process\
-  \ text for consistency in encoding and punctuation, and to manage expectations for\
-  \ questions on topics outside the training data.\n        "
+tags:
+- generated_from_trainer
+datasets:
+- squad_v2
 model-index:
-- name: distilbert-finetuned-uncased
-  results:
-  - task:
-      type: question-answering
-    dataset:
-      name: SQuAD v2
-      type: squad_v2
-    metrics:
-    - type: Exact
-      value: 100.0
-    - type: F1
-      value: 100.0
-    - type: Total
-      value: 2
-    - type: Hasans Exact
-      value: 100.0
-    - type: Hasans F1
-      value: 100.0
-    - type: Hasans Total
-      value: 2
-    - type: Best Exact
-      value: 100.0
-    - type: Best Exact Thresh
-      value: 0.967875599861145
-    - type: Best F1
-      value: 100.0
-    - type: Best F1 Thresh
-      value: 0.967875599861145
-    - type: Total Time In Seconds
-      value: 0.03484977200002959
-    - type: Samples Per Second
-      value: 57.389184640814925
-    - type: Latency In Seconds
-      value: 0.017424886000014794
+- name: distilbert-finetuned-uncased-squad_v2
+  results: []
 ---
 
-# 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]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** en
-- **License:** mit
-- **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 Data 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 Data 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]
-
-
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# distilbert-finetuned-uncased-squad_v2
+
+This model was trained from scratch on the squad_v2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2617
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.6437        | 0.39  | 100  | 2.1780          |
+| 2.1596        | 0.78  | 200  | 1.6557          |
+| 1.8138        | 1.18  | 300  | 1.5683          |
+| 1.6987        | 1.57  | 400  | 1.5076          |
+| 1.6586        | 1.96  | 500  | 1.5350          |
+| 1.5957        | 1.18  | 600  | 1.4431          |
+| 1.5825        | 1.37  | 700  | 1.4955          |
+| 1.5523        | 1.57  | 800  | 1.4444          |
+| 1.5346        | 1.76  | 900  | 1.3930          |
+| 1.5098        | 1.96  | 1000 | 1.4285          |
+| 1.4632        | 2.16  | 1100 | 1.3630          |
+| 1.4468        | 2.35  | 1200 | 1.3710          |
+| 1.4343        | 2.55  | 1300 | 1.3422          |
+| 1.4225        | 2.75  | 1400 | 1.3971          |
+| 1.408         | 2.94  | 1500 | 1.4355          |
+| 1.3609        | 3.14  | 1600 | 1.3332          |
+| 1.3398        | 3.33  | 1700 | 1.3792          |
+| 1.3224        | 3.53  | 1800 | 1.4172          |
+| 1.3152        | 3.73  | 1900 | 1.3956          |
+| 1.3141        | 3.92  | 2000 | 1.3748          |
+| 1.3085        | 2.06  | 2100 | 1.3949          |
+| 1.3325        | 2.16  | 2200 | 1.4870          |
+| 1.3162        | 2.26  | 2300 | 1.4565          |
+| 1.2936        | 2.35  | 2400 | 1.4496          |
+| 1.2648        | 2.45  | 2500 | 1.2868          |
+| 1.2531        | 2.55  | 2600 | 1.5094          |
+| 1.2599        | 2.65  | 2700 | 1.3451          |
+| 1.2545        | 2.75  | 2800 | 1.4071          |
+| 1.2461        | 2.84  | 2900 | 1.3378          |
+| 1.2038        | 2.94  | 3000 | 1.2946          |
+| 1.1677        | 3.04  | 3100 | 1.4802          |
+| 1.103         | 3.14  | 3200 | 1.3580          |
+| 1.1205        | 3.24  | 3300 | 1.3819          |
+| 1.095         | 3.33  | 3400 | 1.4336          |
+| 1.0896        | 3.43  | 3500 | 1.4963          |
+| 1.0856        | 3.53  | 3600 | 1.3384          |
+| 1.0652        | 3.63  | 3700 | 1.3583          |
+| 1.0859        | 3.73  | 3800 | 1.4140          |
+| 1.058         | 3.83  | 3900 | 1.2617          |
+| 1.0724        | 3.92  | 4000 | 1.3552          |
+| 1.0509        | 4.02  | 4100 | 1.2971          |
+| 0.97          | 4.12  | 4200 | 1.3268          |
+| 0.95          | 4.22  | 4300 | 1.3754          |
+| 0.9337        | 4.32  | 4400 | 1.3687          |
+| 0.977         | 4.41  | 4500 | 1.3613          |
+| 0.9484        | 4.51  | 4600 | 1.5139          |
+| 0.9739        | 4.61  | 4700 | 1.2861          |
+| 0.955         | 4.71  | 4800 | 1.3667          |
+| 0.9536        | 4.81  | 4900 | 1.3180          |
+| 0.9541        | 4.9   | 5000 | 1.4611          |
+| 0.9462        | 5.0   | 5100 | 1.4067          |
+| 0.8728        | 5.1   | 5200 | 1.3490          |
+| 0.8646        | 5.2   | 5300 | 1.4631          |
+| 0.8683        | 5.3   | 5400 | 1.4978          |
+| 0.8571        | 5.39  | 5500 | 1.5814          |
+| 0.8475        | 5.49  | 5600 | 1.5535          |
+| 0.8653        | 5.59  | 5700 | 1.4938          |
+| 0.8664        | 5.69  | 5800 | 1.4141          |
+| 0.889         | 5.79  | 5900 | 1.4487          |
+| 0.8601        | 5.88  | 6000 | 1.4722          |
+| 0.8645        | 5.98  | 6100 | 1.5843          |
+| 0.785         | 6.08  | 6200 | 1.6028          |
+| 0.7711        | 6.18  | 6300 | 1.6271          |
+| 0.8056        | 6.28  | 6400 | 1.5399          |
+| 0.8087        | 6.37  | 6500 | 1.4927          |
+| 0.7859        | 6.47  | 6600 | 1.4677          |
+| 0.7896        | 6.57  | 6700 | 1.4780          |
+| 0.7971        | 6.67  | 6800 | 1.5110          |
+| 0.7952        | 6.77  | 6900 | 1.5459          |
+| 0.7971        | 6.87  | 7000 | 1.5282          |
+| 0.7908        | 6.96  | 7100 | 1.4799          |
+| 0.7456        | 7.06  | 7200 | 1.6487          |
+| 0.7236        | 7.16  | 7300 | 1.6543          |
+| 0.7484        | 7.26  | 7400 | 1.6202          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

metrics.json

@@ -6,10 +6,10 @@
     "HasAns_f1": 100.0,
     "HasAns_total": 2,
     "best_exact": 100.0,
-    "best_exact_thresh": 0.7474104762077332,
+    "best_exact_thresh": 0.967875599861145,
     "best_f1": 100.0,
-    "best_f1_thresh": 0.7474104762077332,
-    "total_time_in_seconds": 0.022410528003092622,
-    "samples_per_second": 89.24376970163321,
-    "latency_in_seconds": 0.011205264001546311
+    "best_f1_thresh": 0.967875599861145,
+    "total_time_in_seconds": 0.03484977200002959,
+    "samples_per_second": 57.389184640814925,
+    "latency_in_seconds": 0.017424886000014794
 }

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3331981897354126,
-  "best_model_checkpoint": "/content/drive/My Drive/Colab Notebooks/aai520-project/checkpoints/distilbert-finetuned-uncased/checkpoint-1600",
-  "epoch": 3.9215686274509802,
+  "best_metric": 1.2616792917251587,
+  "best_model_checkpoint": "/content/drive/My Drive/Colab Notebooks/aai520-project/checkpoints/distilbert-finetuned-uncased/checkpoint-3900",
+  "epoch": 7.257416033341506,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 7400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -288,29 +288,785 @@
       "eval_steps_per_second": 22.246,
       "step": 2000
     },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.587831207065751e-05,
+      "loss": 1.3085,
+      "step": 2100
+    },
+    {
+      "epoch": 2.06,
+      "eval_loss": 1.3948506116867065,
+      "eval_runtime": 61.1737,
+      "eval_samples_per_second": 195.656,
+      "eval_steps_per_second": 6.13,
+      "step": 2100
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.5682041216879295e-05,
+      "loss": 1.3325,
+      "step": 2200
+    },
+    {
+      "epoch": 2.16,
+      "eval_loss": 1.4869881868362427,
+      "eval_runtime": 61.232,
+      "eval_samples_per_second": 195.47,
+      "eval_steps_per_second": 6.124,
+      "step": 2200
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 1.548577036310108e-05,
+      "loss": 1.3162,
+      "step": 2300
+    },
+    {
+      "epoch": 2.26,
+      "eval_loss": 1.4565335512161255,
+      "eval_runtime": 61.2209,
+      "eval_samples_per_second": 195.505,
+      "eval_steps_per_second": 6.125,
+      "step": 2300
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 1.5289499509322867e-05,
+      "loss": 1.2936,
+      "step": 2400
+    },
+    {
+      "epoch": 2.35,
+      "eval_loss": 1.449613332748413,
+      "eval_runtime": 61.2023,
+      "eval_samples_per_second": 195.565,
+      "eval_steps_per_second": 6.127,
+      "step": 2400
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.5093228655544654e-05,
+      "loss": 1.2648,
+      "step": 2500
+    },
+    {
+      "epoch": 2.45,
+      "eval_loss": 1.2867687940597534,
+      "eval_runtime": 61.2092,
+      "eval_samples_per_second": 195.542,
+      "eval_steps_per_second": 6.127,
+      "step": 2500
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.4896957801766438e-05,
+      "loss": 1.2531,
+      "step": 2600
+    },
+    {
+      "epoch": 2.55,
+      "eval_loss": 1.5093618631362915,
+      "eval_runtime": 60.9769,
+      "eval_samples_per_second": 196.287,
+      "eval_steps_per_second": 6.15,
+      "step": 2600
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 1.4700686947988226e-05,
+      "loss": 1.2599,
+      "step": 2700
+    },
+    {
+      "epoch": 2.65,
+      "eval_loss": 1.3450872898101807,
+      "eval_runtime": 61.0675,
+      "eval_samples_per_second": 195.996,
+      "eval_steps_per_second": 6.141,
+      "step": 2700
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.4504416094210011e-05,
+      "loss": 1.2545,
+      "step": 2800
+    },
+    {
+      "epoch": 2.75,
+      "eval_loss": 1.407065749168396,
+      "eval_runtime": 61.1333,
+      "eval_samples_per_second": 195.785,
+      "eval_steps_per_second": 6.134,
+      "step": 2800
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.4308145240431797e-05,
+      "loss": 1.2461,
+      "step": 2900
+    },
+    {
+      "epoch": 2.84,
+      "eval_loss": 1.3378450870513916,
+      "eval_runtime": 61.1961,
+      "eval_samples_per_second": 195.584,
+      "eval_steps_per_second": 6.128,
+      "step": 2900
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.4111874386653583e-05,
+      "loss": 1.2038,
+      "step": 3000
+    },
+    {
+      "epoch": 2.94,
+      "eval_loss": 1.294646143913269,
+      "eval_runtime": 61.1636,
+      "eval_samples_per_second": 195.688,
+      "eval_steps_per_second": 6.131,
+      "step": 3000
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 1.391560353287537e-05,
+      "loss": 1.1677,
+      "step": 3100
+    },
+    {
+      "epoch": 3.04,
+      "eval_loss": 1.480231761932373,
+      "eval_runtime": 61.0678,
+      "eval_samples_per_second": 195.995,
+      "eval_steps_per_second": 6.141,
+      "step": 3100
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 1.3719332679097154e-05,
+      "loss": 1.103,
+      "step": 3200
+    },
+    {
+      "epoch": 3.14,
+      "eval_loss": 1.3580176830291748,
+      "eval_runtime": 61.18,
+      "eval_samples_per_second": 195.636,
+      "eval_steps_per_second": 6.129,
+      "step": 3200
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 1.3523061825318942e-05,
+      "loss": 1.1205,
+      "step": 3300
+    },
+    {
+      "epoch": 3.24,
+      "eval_loss": 1.3818870782852173,
+      "eval_runtime": 60.9958,
+      "eval_samples_per_second": 196.227,
+      "eval_steps_per_second": 6.148,
+      "step": 3300
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 1.3326790971540726e-05,
+      "loss": 1.095,
+      "step": 3400
+    },
+    {
+      "epoch": 3.33,
+      "eval_loss": 1.4335613250732422,
+      "eval_runtime": 61.1187,
+      "eval_samples_per_second": 195.832,
+      "eval_steps_per_second": 6.136,
+      "step": 3400
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 1.3130520117762513e-05,
+      "loss": 1.0896,
+      "step": 3500
+    },
+    {
+      "epoch": 3.43,
+      "eval_loss": 1.4962539672851562,
+      "eval_runtime": 61.0543,
+      "eval_samples_per_second": 196.039,
+      "eval_steps_per_second": 6.142,
+      "step": 3500
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 1.2934249263984299e-05,
+      "loss": 1.0856,
+      "step": 3600
+    },
+    {
+      "epoch": 3.53,
+      "eval_loss": 1.3384228944778442,
+      "eval_runtime": 61.1027,
+      "eval_samples_per_second": 195.883,
+      "eval_steps_per_second": 6.137,
+      "step": 3600
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 1.2737978410206085e-05,
+      "loss": 1.0652,
+      "step": 3700
+    },
+    {
+      "epoch": 3.63,
+      "eval_loss": 1.3583240509033203,
+      "eval_runtime": 61.0826,
+      "eval_samples_per_second": 195.948,
+      "eval_steps_per_second": 6.139,
+      "step": 3700
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1.254170755642787e-05,
+      "loss": 1.0859,
+      "step": 3800
+    },
+    {
+      "epoch": 3.73,
+      "eval_loss": 1.414008378982544,
+      "eval_runtime": 61.0681,
+      "eval_samples_per_second": 195.994,
+      "eval_steps_per_second": 6.141,
+      "step": 3800
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 1.2345436702649658e-05,
+      "loss": 1.058,
+      "step": 3900
+    },
+    {
+      "epoch": 3.83,
+      "eval_loss": 1.2616792917251587,
+      "eval_runtime": 61.1143,
+      "eval_samples_per_second": 195.846,
+      "eval_steps_per_second": 6.136,
+      "step": 3900
+    },
     {
       "epoch": 3.92,
-      "step": 2000,
-      "total_flos": 8.35881951136727e+16,
-      "train_loss": 0.0,
-      "train_runtime": 0.4632,
-      "train_samples_per_second": 1126881.683,
-      "train_steps_per_second": 2201.902
+      "learning_rate": 1.2149165848871442e-05,
+      "loss": 1.0724,
+      "step": 4000
     },
     {
       "epoch": 3.92,
-      "eval_loss": 1.3331990242004395,
-      "eval_runtime": 8.4546,
-      "eval_samples_per_second": 1415.675,
-      "eval_steps_per_second": 11.118,
-      "step": 2000
+      "eval_loss": 1.3551816940307617,
+      "eval_runtime": 61.0974,
+      "eval_samples_per_second": 195.9,
+      "eval_steps_per_second": 6.138,
+      "step": 4000
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 1.1954857703631012e-05,
+      "loss": 1.0509,
+      "step": 4100
+    },
+    {
+      "epoch": 4.02,
+      "eval_loss": 1.2970877885818481,
+      "eval_runtime": 61.0416,
+      "eval_samples_per_second": 196.079,
+      "eval_steps_per_second": 6.143,
+      "step": 4100
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 1.1758586849852797e-05,
+      "loss": 0.97,
+      "step": 4200
+    },
+    {
+      "epoch": 4.12,
+      "eval_loss": 1.3268026113510132,
+      "eval_runtime": 61.0438,
+      "eval_samples_per_second": 196.072,
+      "eval_steps_per_second": 6.143,
+      "step": 4200
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 1.1562315996074585e-05,
+      "loss": 0.95,
+      "step": 4300
+    },
+    {
+      "epoch": 4.22,
+      "eval_loss": 1.3753584623336792,
+      "eval_runtime": 61.1527,
+      "eval_samples_per_second": 195.723,
+      "eval_steps_per_second": 6.132,
+      "step": 4300
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 1.1366045142296369e-05,
+      "loss": 0.9337,
+      "step": 4400
+    },
+    {
+      "epoch": 4.32,
+      "eval_loss": 1.3687292337417603,
+      "eval_runtime": 61.1591,
+      "eval_samples_per_second": 195.703,
+      "eval_steps_per_second": 6.132,
+      "step": 4400
+    },
+    {
+      "epoch": 4.41,
+      "learning_rate": 1.1169774288518156e-05,
+      "loss": 0.977,
+      "step": 4500
+    },
+    {
+      "epoch": 4.41,
+      "eval_loss": 1.3613475561141968,
+      "eval_runtime": 61.1865,
+      "eval_samples_per_second": 195.615,
+      "eval_steps_per_second": 6.129,
+      "step": 4500
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 1.0973503434739942e-05,
+      "loss": 0.9484,
+      "step": 4600
+    },
+    {
+      "epoch": 4.51,
+      "eval_loss": 1.513939380645752,
+      "eval_runtime": 61.2246,
+      "eval_samples_per_second": 195.493,
+      "eval_steps_per_second": 6.125,
+      "step": 4600
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 1.0777232580961728e-05,
+      "loss": 0.9739,
+      "step": 4700
+    },
+    {
+      "epoch": 4.61,
+      "eval_loss": 1.2861210107803345,
+      "eval_runtime": 61.1721,
+      "eval_samples_per_second": 195.661,
+      "eval_steps_per_second": 6.13,
+      "step": 4700
+    },
+    {
+      "epoch": 4.71,
+      "learning_rate": 1.0580961727183514e-05,
+      "loss": 0.955,
+      "step": 4800
+    },
+    {
+      "epoch": 4.71,
+      "eval_loss": 1.3666507005691528,
+      "eval_runtime": 61.1291,
+      "eval_samples_per_second": 195.799,
+      "eval_steps_per_second": 6.135,
+      "step": 4800
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 1.0384690873405301e-05,
+      "loss": 0.9536,
+      "step": 4900
+    },
+    {
+      "epoch": 4.81,
+      "eval_loss": 1.3179610967636108,
+      "eval_runtime": 61.1785,
+      "eval_samples_per_second": 195.641,
+      "eval_steps_per_second": 6.13,
+      "step": 4900
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 1.0188420019627085e-05,
+      "loss": 0.9541,
+      "step": 5000
+    },
+    {
+      "epoch": 4.9,
+      "eval_loss": 1.4610702991485596,
+      "eval_runtime": 61.0871,
+      "eval_samples_per_second": 195.933,
+      "eval_steps_per_second": 6.139,
+      "step": 5000
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 9.992149165848873e-06,
+      "loss": 0.9462,
+      "step": 5100
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.4066604375839233,
+      "eval_runtime": 61.1331,
+      "eval_samples_per_second": 195.786,
+      "eval_steps_per_second": 6.134,
+      "step": 5100
+    },
+    {
+      "epoch": 5.1,
+      "learning_rate": 9.795878312070658e-06,
+      "loss": 0.8728,
+      "step": 5200
+    },
+    {
+      "epoch": 5.1,
+      "eval_loss": 1.3490474224090576,
+      "eval_runtime": 61.0973,
+      "eval_samples_per_second": 195.901,
+      "eval_steps_per_second": 6.138,
+      "step": 5200
+    },
+    {
+      "epoch": 5.2,
+      "learning_rate": 9.599607458292444e-06,
+      "loss": 0.8646,
+      "step": 5300
+    },
+    {
+      "epoch": 5.2,
+      "eval_loss": 1.4630706310272217,
+      "eval_runtime": 61.0445,
+      "eval_samples_per_second": 196.07,
+      "eval_steps_per_second": 6.143,
+      "step": 5300
+    },
+    {
+      "epoch": 5.3,
+      "learning_rate": 9.40333660451423e-06,
+      "loss": 0.8683,
+      "step": 5400
+    },
+    {
+      "epoch": 5.3,
+      "eval_loss": 1.4977810382843018,
+      "eval_runtime": 61.0754,
+      "eval_samples_per_second": 195.971,
+      "eval_steps_per_second": 6.14,
+      "step": 5400
+    },
+    {
+      "epoch": 5.39,
+      "learning_rate": 9.207065750736016e-06,
+      "loss": 0.8571,
+      "step": 5500
+    },
+    {
+      "epoch": 5.39,
+      "eval_loss": 1.5814284086227417,
+      "eval_runtime": 61.0641,
+      "eval_samples_per_second": 196.007,
+      "eval_steps_per_second": 6.141,
+      "step": 5500
+    },
+    {
+      "epoch": 5.49,
+      "learning_rate": 9.010794896957803e-06,
+      "loss": 0.8475,
+      "step": 5600
+    },
+    {
+      "epoch": 5.49,
+      "eval_loss": 1.5535171031951904,
+      "eval_runtime": 61.1062,
+      "eval_samples_per_second": 195.872,
+      "eval_steps_per_second": 6.137,
+      "step": 5600
+    },
+    {
+      "epoch": 5.59,
+      "learning_rate": 8.814524043179589e-06,
+      "loss": 0.8653,
+      "step": 5700
+    },
+    {
+      "epoch": 5.59,
+      "eval_loss": 1.4938398599624634,
+      "eval_runtime": 61.1584,
+      "eval_samples_per_second": 195.705,
+      "eval_steps_per_second": 6.132,
+      "step": 5700
+    },
+    {
+      "epoch": 5.69,
+      "learning_rate": 8.618253189401375e-06,
+      "loss": 0.8664,
+      "step": 5800
+    },
+    {
+      "epoch": 5.69,
+      "eval_loss": 1.414058804512024,
+      "eval_runtime": 61.1886,
+      "eval_samples_per_second": 195.608,
+      "eval_steps_per_second": 6.129,
+      "step": 5800
+    },
+    {
+      "epoch": 5.79,
+      "learning_rate": 8.42198233562316e-06,
+      "loss": 0.889,
+      "step": 5900
+    },
+    {
+      "epoch": 5.79,
+      "eval_loss": 1.4486888647079468,
+      "eval_runtime": 61.1387,
+      "eval_samples_per_second": 195.768,
+      "eval_steps_per_second": 6.134,
+      "step": 5900
+    },
+    {
+      "epoch": 5.88,
+      "learning_rate": 8.225711481844946e-06,
+      "loss": 0.8601,
+      "step": 6000
+    },
+    {
+      "epoch": 5.88,
+      "eval_loss": 1.47215735912323,
+      "eval_runtime": 61.1249,
+      "eval_samples_per_second": 195.812,
+      "eval_steps_per_second": 6.135,
+      "step": 6000
+    },
+    {
+      "epoch": 5.98,
+      "learning_rate": 8.031403336604516e-06,
+      "loss": 0.8645,
+      "step": 6100
+    },
+    {
+      "epoch": 5.98,
+      "eval_loss": 1.5842609405517578,
+      "eval_runtime": 61.0783,
+      "eval_samples_per_second": 195.962,
+      "eval_steps_per_second": 6.14,
+      "step": 6100
+    },
+    {
+      "epoch": 6.08,
+      "learning_rate": 7.835132482826301e-06,
+      "loss": 0.785,
+      "step": 6200
+    },
+    {
+      "epoch": 6.08,
+      "eval_loss": 1.6027640104293823,
+      "eval_runtime": 61.1172,
+      "eval_samples_per_second": 195.837,
+      "eval_steps_per_second": 6.136,
+      "step": 6200
+    },
+    {
+      "epoch": 6.18,
+      "learning_rate": 7.638861629048087e-06,
+      "loss": 0.7711,
+      "step": 6300
+    },
+    {
+      "epoch": 6.18,
+      "eval_loss": 1.6270956993103027,
+      "eval_runtime": 61.0612,
+      "eval_samples_per_second": 196.016,
+      "eval_steps_per_second": 6.141,
+      "step": 6300
+    },
+    {
+      "epoch": 6.28,
+      "learning_rate": 7.442590775269874e-06,
+      "loss": 0.8056,
+      "step": 6400
+    },
+    {
+      "epoch": 6.28,
+      "eval_loss": 1.5399292707443237,
+      "eval_runtime": 61.1714,
+      "eval_samples_per_second": 195.663,
+      "eval_steps_per_second": 6.13,
+      "step": 6400
+    },
+    {
+      "epoch": 6.37,
+      "learning_rate": 7.246319921491659e-06,
+      "loss": 0.8087,
+      "step": 6500
+    },
+    {
+      "epoch": 6.37,
+      "eval_loss": 1.492693305015564,
+      "eval_runtime": 61.0261,
+      "eval_samples_per_second": 196.129,
+      "eval_steps_per_second": 6.145,
+      "step": 6500
+    },
+    {
+      "epoch": 6.47,
+      "learning_rate": 7.0500490677134445e-06,
+      "loss": 0.7859,
+      "step": 6600
+    },
+    {
+      "epoch": 6.47,
+      "eval_loss": 1.4677467346191406,
+      "eval_runtime": 61.0807,
+      "eval_samples_per_second": 195.954,
+      "eval_steps_per_second": 6.139,
+      "step": 6600
+    },
+    {
+      "epoch": 6.57,
+      "learning_rate": 6.853778213935232e-06,
+      "loss": 0.7896,
+      "step": 6700
+    },
+    {
+      "epoch": 6.57,
+      "eval_loss": 1.4780325889587402,
+      "eval_runtime": 61.0973,
+      "eval_samples_per_second": 195.901,
+      "eval_steps_per_second": 6.138,
+      "step": 6700
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 6.657507360157017e-06,
+      "loss": 0.7971,
+      "step": 6800
+    },
+    {
+      "epoch": 6.67,
+      "eval_loss": 1.5110238790512085,
+      "eval_runtime": 61.1306,
+      "eval_samples_per_second": 195.794,
+      "eval_steps_per_second": 6.134,
+      "step": 6800
+    },
+    {
+      "epoch": 6.77,
+      "learning_rate": 6.461236506378803e-06,
+      "loss": 0.7952,
+      "step": 6900
+    },
+    {
+      "epoch": 6.77,
+      "eval_loss": 1.545872688293457,
+      "eval_runtime": 61.0099,
+      "eval_samples_per_second": 196.181,
+      "eval_steps_per_second": 6.147,
+      "step": 6900
+    },
+    {
+      "epoch": 6.87,
+      "learning_rate": 6.26496565260059e-06,
+      "loss": 0.7971,
+      "step": 7000
+    },
+    {
+      "epoch": 6.87,
+      "eval_loss": 1.5281697511672974,
+      "eval_runtime": 61.0816,
+      "eval_samples_per_second": 195.951,
+      "eval_steps_per_second": 6.139,
+      "step": 7000
+    },
+    {
+      "epoch": 6.96,
+      "learning_rate": 6.068694798822376e-06,
+      "loss": 0.7908,
+      "step": 7100
+    },
+    {
+      "epoch": 6.96,
+      "eval_loss": 1.4799116849899292,
+      "eval_runtime": 61.1305,
+      "eval_samples_per_second": 195.794,
+      "eval_steps_per_second": 6.134,
+      "step": 7100
+    },
+    {
+      "epoch": 7.06,
+      "learning_rate": 5.872423945044161e-06,
+      "loss": 0.7456,
+      "step": 7200
+    },
+    {
+      "epoch": 7.06,
+      "eval_loss": 1.6487486362457275,
+      "eval_runtime": 61.0413,
+      "eval_samples_per_second": 196.08,
+      "eval_steps_per_second": 6.143,
+      "step": 7200
+    },
+    {
+      "epoch": 7.16,
+      "learning_rate": 5.676153091265948e-06,
+      "loss": 0.7236,
+      "step": 7300
+    },
+    {
+      "epoch": 7.16,
+      "eval_loss": 1.654253602027893,
+      "eval_runtime": 61.1832,
+      "eval_samples_per_second": 195.626,
+      "eval_steps_per_second": 6.129,
+      "step": 7300
+    },
+    {
+      "epoch": 7.26,
+      "learning_rate": 5.479882237487734e-06,
+      "loss": 0.7484,
+      "step": 7400
+    },
+    {
+      "epoch": 7.26,
+      "eval_loss": 1.6202023029327393,
+      "eval_runtime": 61.1291,
+      "eval_samples_per_second": 195.799,
+      "eval_steps_per_second": 6.135,
+      "step": 7400
+    },
+    {
+      "epoch": 7.26,
+      "step": 7400,
+      "total_flos": 1.738708177538776e+17,
+      "train_loss": 0.0,
+      "train_runtime": 0.8545,
+      "train_samples_per_second": 1527321.888,
+      "train_steps_per_second": 2984.353
+    },
+    {
+      "epoch": 7.26,
+      "eval_loss": 1.261675477027893,
+      "eval_runtime": 63.4844,
+      "eval_samples_per_second": 188.535,
+      "eval_steps_per_second": 1.481,
+      "step": 7400
     }
   ],
   "logging_steps": 100,
-  "max_steps": 1020,
-  "num_train_epochs": 4,
+  "max_steps": 2550,
+  "num_train_epochs": 10,
   "save_steps": 100,
-  "total_flos": 8.35881951136727e+16,
+  "total_flos": 1.738708177538776e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec995f22a550259b8395d0763625d078960b524379b4835c2d7be674d0fe65a
+oid sha256:afec34369fc19baa258a16d4008e51527e903540998c874694601e1fcafb68b7
 size 4664