Checkpoint 91770

README.md

@@ -1,76 +1,202 @@
 ---
-license: apache-2.0
 library_name: peft
-tags:
-- generated_from_trainer
 base_model: google/flan-t5-xl
-model-index:
-- name: flan-t5-xl-spider-dict_qpl-20240304-v3
-  results: []
 ---
 
-<!-- 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. -->
+# Model Card for Model ID
 
-# flan-t5-xl-spider-dict_qpl-20240304-v3
+<!-- Provide a quick summary of what the model is/does. -->
 
-This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.0957
-- Execution Accuracy: 69.3424
 
-## Model description
 
-More information needed
+## Model Details
 
-## Intended uses & limitations
+### Model Description
 
-More information needed
+<!-- Provide a longer summary of what this model is. -->
 
-## Training and evaluation data
 
-More information needed
 
-## Training procedure
+- **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]
 
-### Training hyperparameters
+### Model Sources [optional]
 
-The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 1
-- eval_batch_size: 8
-- seed: 1
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 17
+<!-- Provide the basic links for the model. -->
 
-### Training results
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
 
-| Training Loss | Epoch | Step   | Execution Accuracy | Validation Loss |
-|:-------------:|:-----:|:------:|:------------------:|:---------------:|
-| 0.068         | 1.0   | 6555   | 39.4584            | 0.0767          |
-| 0.0432        | 2.0   | 13110  | 52.9981            | 0.0608          |
-| 0.033         | 3.0   | 19665  | 60.3482            | 0.0612          |
-| 0.0297        | 4.0   | 26220  | 62.8627            | 0.0589          |
-| 0.0213        | 5.0   | 32775  | 64.1199            | 0.0605          |
-| 0.0188        | 6.0   | 39330  | 64.3133            | 0.0619          |
-| 0.0166        | 7.0   | 45885  | 66.441             | 0.0611          |
-| 0.0162        | 8.0   | 52440  | 65.8607            | 0.0669          |
-| 0.0109        | 9.0   | 58995  | 68.9555            | 0.0666          |
-| 0.0101        | 10.0  | 65550  | 68.1818            | 0.0736          |
-| 0.0085        | 11.0  | 72105  | 68.0851            | 0.0764          |
-| 0.0069        | 12.0  | 78660  | 69.0522            | 0.0801          |
-| 0.0068        | 13.0  | 85215  | 69.2456            | 0.0884          |
-| 0.0052        | 14.0  | 91770  | 70.793             | 0.0883          |
-| 0.0039        | 15.0  | 98325  | 70.5029            | 0.0936          |
-| 0.005         | 16.0  | 104880 | 67.9884            | 0.0904          |
-| 0.0042        | 17.0  | 111435 | 0.0957             | 69.3424         |
+## 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 0.9.0
-- Transformers 4.38.2
-- Pytorch 2.1.0+cu118
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- PEFT 0.9.0

trainer_state.json

@@ -0,0 +1,1428 @@
+{
+  "best_metric": 70.793,
+  "best_model_checkpoint": "flan-t5-xl-spider-dict_qpl-20240304-v3/checkpoint-91770",
+  "epoch": 14.0,
+  "eval_steps": 500,
+  "global_step": 91770,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.1395843029022217,
+      "learning_rate": 0.0001989829646580219,
+      "loss": 1.1111,
+      "step": 500
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.5051442384719849,
+      "learning_rate": 0.00019796592931604375,
+      "loss": 0.2196,
+      "step": 1000
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.0700268745422363,
+      "learning_rate": 0.00019694889397406563,
+      "loss": 0.1653,
+      "step": 1500
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.6627328395843506,
+      "learning_rate": 0.00019593185863208746,
+      "loss": 0.1313,
+      "step": 2000
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.8090806603431702,
+      "learning_rate": 0.00019491482329010934,
+      "loss": 0.1141,
+      "step": 2500
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.5775860548019409,
+      "learning_rate": 0.0001938977879481312,
+      "loss": 0.1071,
+      "step": 3000
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.548545777797699,
+      "learning_rate": 0.00019288075260615308,
+      "loss": 0.0963,
+      "step": 3500
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.8567075729370117,
+      "learning_rate": 0.00019186371726417494,
+      "loss": 0.0852,
+      "step": 4000
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.2921431064605713,
+      "learning_rate": 0.00019084668192219682,
+      "loss": 0.0787,
+      "step": 4500
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.1600842922925949,
+      "learning_rate": 0.00018982964658021868,
+      "loss": 0.0789,
+      "step": 5000
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.48446208238601685,
+      "learning_rate": 0.00018881261123824053,
+      "loss": 0.0732,
+      "step": 5500
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5679713487625122,
+      "learning_rate": 0.0001877955758962624,
+      "loss": 0.0699,
+      "step": 6000
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.3154789209365845,
+      "learning_rate": 0.00018677854055428427,
+      "loss": 0.068,
+      "step": 6500
+    },
+    {
+      "epoch": 1.0,
+      "eval_execution_accuracy": 39.4584,
+      "eval_loss": 0.0767175704240799,
+      "eval_runtime": 1448.6397,
+      "eval_samples_per_second": 0.714,
+      "eval_steps_per_second": 0.09,
+      "step": 6555
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.3169132173061371,
+      "learning_rate": 0.00018576150521230613,
+      "loss": 0.0608,
+      "step": 7000
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.5822262763977051,
+      "learning_rate": 0.000184744469870328,
+      "loss": 0.0594,
+      "step": 7500
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.39004069566726685,
+      "learning_rate": 0.00018372743452834986,
+      "loss": 0.0601,
+      "step": 8000
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.48953133821487427,
+      "learning_rate": 0.00018271039918637175,
+      "loss": 0.0563,
+      "step": 8500
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.24563811719417572,
+      "learning_rate": 0.0001816933638443936,
+      "loss": 0.0547,
+      "step": 9000
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.028272481635212898,
+      "learning_rate": 0.00018067632850241546,
+      "loss": 0.0513,
+      "step": 9500
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.5085881948471069,
+      "learning_rate": 0.00017965929316043731,
+      "loss": 0.054,
+      "step": 10000
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.3579294681549072,
+      "learning_rate": 0.0001786422578184592,
+      "loss": 0.0523,
+      "step": 10500
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.717029869556427,
+      "learning_rate": 0.00017762522247648105,
+      "loss": 0.048,
+      "step": 11000
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.5166067481040955,
+      "learning_rate": 0.00017660818713450294,
+      "loss": 0.0494,
+      "step": 11500
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.7487884759902954,
+      "learning_rate": 0.0001755911517925248,
+      "loss": 0.0444,
+      "step": 12000
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.24778613448143005,
+      "learning_rate": 0.00017457411645054667,
+      "loss": 0.0427,
+      "step": 12500
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.3205878436565399,
+      "learning_rate": 0.00017355708110856853,
+      "loss": 0.0432,
+      "step": 13000
+    },
+    {
+      "epoch": 2.0,
+      "eval_execution_accuracy": 52.9981,
+      "eval_loss": 0.06084170565009117,
+      "eval_runtime": 1830.3328,
+      "eval_samples_per_second": 0.565,
+      "eval_steps_per_second": 0.071,
+      "step": 13110
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 0.424517959356308,
+      "learning_rate": 0.00017254004576659039,
+      "loss": 0.0422,
+      "step": 13500
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 0.5932648777961731,
+      "learning_rate": 0.00017152301042461227,
+      "loss": 0.0447,
+      "step": 14000
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 0.1377120316028595,
+      "learning_rate": 0.00017050597508263412,
+      "loss": 0.0399,
+      "step": 14500
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 0.257429301738739,
+      "learning_rate": 0.000169488939740656,
+      "loss": 0.0361,
+      "step": 15000
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.18395432829856873,
+      "learning_rate": 0.00016847190439867786,
+      "loss": 0.038,
+      "step": 15500
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.526056706905365,
+      "learning_rate": 0.00016745486905669975,
+      "loss": 0.0343,
+      "step": 16000
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.17391307651996613,
+      "learning_rate": 0.0001664378337147216,
+      "loss": 0.0357,
+      "step": 16500
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 0.2732052505016327,
+      "learning_rate": 0.00016542079837274346,
+      "loss": 0.0366,
+      "step": 17000
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 0.3006477355957031,
+      "learning_rate": 0.0001644037630307653,
+      "loss": 0.033,
+      "step": 17500
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.011468607001006603,
+      "learning_rate": 0.0001633867276887872,
+      "loss": 0.0335,
+      "step": 18000
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 0.5990091562271118,
+      "learning_rate": 0.00016236969234680905,
+      "loss": 0.0355,
+      "step": 18500
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.29567310214042664,
+      "learning_rate": 0.00016135265700483093,
+      "loss": 0.0337,
+      "step": 19000
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 0.006056224461644888,
+      "learning_rate": 0.0001603356216628528,
+      "loss": 0.033,
+      "step": 19500
+    },
+    {
+      "epoch": 3.0,
+      "eval_execution_accuracy": 60.3482,
+      "eval_loss": 0.06122712045907974,
+      "eval_runtime": 1764.8897,
+      "eval_samples_per_second": 0.586,
+      "eval_steps_per_second": 0.074,
+      "step": 19665
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 0.30340930819511414,
+      "learning_rate": 0.00015931858632087467,
+      "loss": 0.0297,
+      "step": 20000
+    },
+    {
+      "epoch": 3.13,
+      "grad_norm": 0.017457757145166397,
+      "learning_rate": 0.00015830155097889653,
+      "loss": 0.0305,
+      "step": 20500
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.254963755607605,
+      "learning_rate": 0.00015728451563691838,
+      "loss": 0.028,
+      "step": 21000
+    },
+    {
+      "epoch": 3.28,
+      "grad_norm": 0.8444741368293762,
+      "learning_rate": 0.00015626748029494024,
+      "loss": 0.027,
+      "step": 21500
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 0.47470298409461975,
+      "learning_rate": 0.00015525044495296212,
+      "loss": 0.0297,
+      "step": 22000
+    },
+    {
+      "epoch": 3.43,
+      "grad_norm": 0.08465476334095001,
+      "learning_rate": 0.00015423340961098398,
+      "loss": 0.0288,
+      "step": 22500
+    },
+    {
+      "epoch": 3.51,
+      "grad_norm": 0.32479336857795715,
+      "learning_rate": 0.00015321637426900586,
+      "loss": 0.0302,
+      "step": 23000
+    },
+    {
+      "epoch": 3.59,
+      "grad_norm": 3.906116008758545,
+      "learning_rate": 0.00015219933892702772,
+      "loss": 0.0297,
+      "step": 23500
+    },
+    {
+      "epoch": 3.66,
+      "grad_norm": 0.821506917476654,
+      "learning_rate": 0.0001511823035850496,
+      "loss": 0.0266,
+      "step": 24000
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 0.36568546295166016,
+      "learning_rate": 0.00015016526824307146,
+      "loss": 0.0296,
+      "step": 24500
+    },
+    {
+      "epoch": 3.81,
+      "grad_norm": 0.6190164089202881,
+      "learning_rate": 0.0001491482329010933,
+      "loss": 0.0287,
+      "step": 25000
+    },
+    {
+      "epoch": 3.89,
+      "grad_norm": 0.2852056920528412,
+      "learning_rate": 0.00014813119755911517,
+      "loss": 0.0271,
+      "step": 25500
+    },
+    {
+      "epoch": 3.97,
+      "grad_norm": 0.10050356388092041,
+      "learning_rate": 0.00014711416221713705,
+      "loss": 0.0297,
+      "step": 26000
+    },
+    {
+      "epoch": 4.0,
+      "eval_execution_accuracy": 62.8627,
+      "eval_loss": 0.0589316301047802,
+      "eval_runtime": 1802.5956,
+      "eval_samples_per_second": 0.574,
+      "eval_steps_per_second": 0.072,
+      "step": 26220
+    },
+    {
+      "epoch": 4.04,
+      "grad_norm": 0.4248579740524292,
+      "learning_rate": 0.00014609712687515893,
+      "loss": 0.027,
+      "step": 26500
+    },
+    {
+      "epoch": 4.12,
+      "grad_norm": 0.5822145342826843,
+      "learning_rate": 0.0001450800915331808,
+      "loss": 0.0234,
+      "step": 27000
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 0.028582902625203133,
+      "learning_rate": 0.00014406305619120267,
+      "loss": 0.0256,
+      "step": 27500
+    },
+    {
+      "epoch": 4.27,
+      "grad_norm": 0.026179086416959763,
+      "learning_rate": 0.00014304602084922453,
+      "loss": 0.0248,
+      "step": 28000
+    },
+    {
+      "epoch": 4.35,
+      "grad_norm": 0.24167686700820923,
+      "learning_rate": 0.00014202898550724638,
+      "loss": 0.024,
+      "step": 28500
+    },
+    {
+      "epoch": 4.42,
+      "grad_norm": 0.21196796000003815,
+      "learning_rate": 0.00014101195016526824,
+      "loss": 0.0232,
+      "step": 29000
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.1384715437889099,
+      "learning_rate": 0.00013999491482329012,
+      "loss": 0.0231,
+      "step": 29500
+    },
+    {
+      "epoch": 4.58,
+      "grad_norm": 0.25323405861854553,
+      "learning_rate": 0.00013897787948131198,
+      "loss": 0.0227,
+      "step": 30000
+    },
+    {
+      "epoch": 4.65,
+      "grad_norm": 0.17340293526649475,
+      "learning_rate": 0.00013796084413933386,
+      "loss": 0.0232,
+      "step": 30500
+    },
+    {
+      "epoch": 4.73,
+      "grad_norm": 0.01007129717618227,
+      "learning_rate": 0.00013694380879735572,
+      "loss": 0.0212,
+      "step": 31000
+    },
+    {
+      "epoch": 4.81,
+      "grad_norm": 0.5236365795135498,
+      "learning_rate": 0.0001359267734553776,
+      "loss": 0.0233,
+      "step": 31500
+    },
+    {
+      "epoch": 4.88,
+      "grad_norm": 0.49340179562568665,
+      "learning_rate": 0.00013490973811339945,
+      "loss": 0.0258,
+      "step": 32000
+    },
+    {
+      "epoch": 4.96,
+      "grad_norm": 0.7839340567588806,
+      "learning_rate": 0.0001338927027714213,
+      "loss": 0.0213,
+      "step": 32500
+    },
+    {
+      "epoch": 5.0,
+      "eval_execution_accuracy": 64.1199,
+      "eval_loss": 0.06054983288049698,
+      "eval_runtime": 1797.3766,
+      "eval_samples_per_second": 0.575,
+      "eval_steps_per_second": 0.072,
+      "step": 32775
+    },
+    {
+      "epoch": 5.03,
+      "grad_norm": 0.47601643204689026,
+      "learning_rate": 0.00013287566742944317,
+      "loss": 0.0198,
+      "step": 33000
+    },
+    {
+      "epoch": 5.11,
+      "grad_norm": 0.3969705402851105,
+      "learning_rate": 0.00013185863208746505,
+      "loss": 0.0201,
+      "step": 33500
+    },
+    {
+      "epoch": 5.19,
+      "grad_norm": 0.06148134917020798,
+      "learning_rate": 0.0001308415967454869,
+      "loss": 0.021,
+      "step": 34000
+    },
+    {
+      "epoch": 5.26,
+      "grad_norm": 0.0021157702431082726,
+      "learning_rate": 0.0001298245614035088,
+      "loss": 0.0189,
+      "step": 34500
+    },
+    {
+      "epoch": 5.34,
+      "grad_norm": 0.09957286715507507,
+      "learning_rate": 0.00012880752606153064,
+      "loss": 0.0214,
+      "step": 35000
+    },
+    {
+      "epoch": 5.42,
+      "grad_norm": 0.0950658768415451,
+      "learning_rate": 0.00012779049071955253,
+      "loss": 0.0206,
+      "step": 35500
+    },
+    {
+      "epoch": 5.49,
+      "grad_norm": 0.5534018874168396,
+      "learning_rate": 0.00012677345537757438,
+      "loss": 0.0182,
+      "step": 36000
+    },
+    {
+      "epoch": 5.57,
+      "grad_norm": 0.21119213104248047,
+      "learning_rate": 0.00012575642003559624,
+      "loss": 0.0195,
+      "step": 36500
+    },
+    {
+      "epoch": 5.64,
+      "grad_norm": 0.10089027881622314,
+      "learning_rate": 0.0001247393846936181,
+      "loss": 0.0196,
+      "step": 37000
+    },
+    {
+      "epoch": 5.72,
+      "grad_norm": 0.36528435349464417,
+      "learning_rate": 0.00012372234935163998,
+      "loss": 0.0187,
+      "step": 37500
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 0.13980288803577423,
+      "learning_rate": 0.00012270531400966183,
+      "loss": 0.0177,
+      "step": 38000
+    },
+    {
+      "epoch": 5.87,
+      "grad_norm": 0.03852877765893936,
+      "learning_rate": 0.00012168827866768371,
+      "loss": 0.0219,
+      "step": 38500
+    },
+    {
+      "epoch": 5.95,
+      "grad_norm": 0.23849190771579742,
+      "learning_rate": 0.00012067124332570557,
+      "loss": 0.0188,
+      "step": 39000
+    },
+    {
+      "epoch": 6.0,
+      "eval_execution_accuracy": 64.3133,
+      "eval_loss": 0.061897873878479004,
+      "eval_runtime": 1866.1394,
+      "eval_samples_per_second": 0.554,
+      "eval_steps_per_second": 0.07,
+      "step": 39330
+    },
+    {
+      "epoch": 6.03,
+      "grad_norm": 0.6830750703811646,
+      "learning_rate": 0.00011965420798372744,
+      "loss": 0.0175,
+      "step": 39500
+    },
+    {
+      "epoch": 6.1,
+      "grad_norm": 0.013556591235101223,
+      "learning_rate": 0.00011863717264174932,
+      "loss": 0.0166,
+      "step": 40000
+    },
+    {
+      "epoch": 6.18,
+      "grad_norm": 0.06067229434847832,
+      "learning_rate": 0.00011762013729977118,
+      "loss": 0.0167,
+      "step": 40500
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 0.815282940864563,
+      "learning_rate": 0.00011660310195779305,
+      "loss": 0.0179,
+      "step": 41000
+    },
+    {
+      "epoch": 6.33,
+      "grad_norm": 0.09995106607675552,
+      "learning_rate": 0.0001155860666158149,
+      "loss": 0.0164,
+      "step": 41500
+    },
+    {
+      "epoch": 6.41,
+      "grad_norm": 0.07753593474626541,
+      "learning_rate": 0.00011456903127383679,
+      "loss": 0.0162,
+      "step": 42000
+    },
+    {
+      "epoch": 6.48,
+      "grad_norm": 0.16108450293540955,
+      "learning_rate": 0.00011355199593185864,
+      "loss": 0.0176,
+      "step": 42500
+    },
+    {
+      "epoch": 6.56,
+      "grad_norm": 0.1027306616306305,
+      "learning_rate": 0.00011253496058988051,
+      "loss": 0.0176,
+      "step": 43000
+    },
+    {
+      "epoch": 6.64,
+      "grad_norm": 0.527164876461029,
+      "learning_rate": 0.00011151792524790237,
+      "loss": 0.0148,
+      "step": 43500
+    },
+    {
+      "epoch": 6.71,
+      "grad_norm": 0.12876121699810028,
+      "learning_rate": 0.00011050088990592425,
+      "loss": 0.016,
+      "step": 44000
+    },
+    {
+      "epoch": 6.79,
+      "grad_norm": 0.07147472351789474,
+      "learning_rate": 0.00010948385456394609,
+      "loss": 0.0166,
+      "step": 44500
+    },
+    {
+      "epoch": 6.86,
+      "grad_norm": 0.11269113421440125,
+      "learning_rate": 0.00010846681922196797,
+      "loss": 0.0159,
+      "step": 45000
+    },
+    {
+      "epoch": 6.94,
+      "grad_norm": 0.0018060138681903481,
+      "learning_rate": 0.00010744978387998983,
+      "loss": 0.0166,
+      "step": 45500
+    },
+    {
+      "epoch": 7.0,
+      "eval_execution_accuracy": 66.441,
+      "eval_loss": 0.06106872484087944,
+      "eval_runtime": 1845.4627,
+      "eval_samples_per_second": 0.56,
+      "eval_steps_per_second": 0.07,
+      "step": 45885
+    },
+    {
+      "epoch": 7.02,
+      "grad_norm": 0.010804968886077404,
+      "learning_rate": 0.00010643274853801171,
+      "loss": 0.0148,
+      "step": 46000
+    },
+    {
+      "epoch": 7.09,
+      "grad_norm": 0.014622188173234463,
+      "learning_rate": 0.00010541571319603355,
+      "loss": 0.0147,
+      "step": 46500
+    },
+    {
+      "epoch": 7.17,
+      "grad_norm": 0.13804876804351807,
+      "learning_rate": 0.00010439867785405544,
+      "loss": 0.015,
+      "step": 47000
+    },
+    {
+      "epoch": 7.25,
+      "grad_norm": 0.0409139022231102,
+      "learning_rate": 0.00010338164251207729,
+      "loss": 0.0126,
+      "step": 47500
+    },
+    {
+      "epoch": 7.32,
+      "grad_norm": 0.11225342750549316,
+      "learning_rate": 0.00010236460717009918,
+      "loss": 0.014,
+      "step": 48000
+    },
+    {
+      "epoch": 7.4,
+      "grad_norm": 0.021166274324059486,
+      "learning_rate": 0.00010134757182812102,
+      "loss": 0.0146,
+      "step": 48500
+    },
+    {
+      "epoch": 7.48,
+      "grad_norm": 0.2523152828216553,
+      "learning_rate": 0.0001003305364861429,
+      "loss": 0.014,
+      "step": 49000
+    },
+    {
+      "epoch": 7.55,
+      "grad_norm": 0.014010763727128506,
+      "learning_rate": 9.931350114416477e-05,
+      "loss": 0.0142,
+      "step": 49500
+    },
+    {
+      "epoch": 7.63,
+      "grad_norm": 0.3102033734321594,
+      "learning_rate": 9.829646580218663e-05,
+      "loss": 0.0131,
+      "step": 50000
+    },
+    {
+      "epoch": 7.7,
+      "grad_norm": 0.00048806238919496536,
+      "learning_rate": 9.72794304602085e-05,
+      "loss": 0.014,
+      "step": 50500
+    },
+    {
+      "epoch": 7.78,
+      "grad_norm": 1.1056194305419922,
+      "learning_rate": 9.626239511823036e-05,
+      "loss": 0.0122,
+      "step": 51000
+    },
+    {
+      "epoch": 7.86,
+      "grad_norm": 0.07580041885375977,
+      "learning_rate": 9.524535977625223e-05,
+      "loss": 0.0118,
+      "step": 51500
+    },
+    {
+      "epoch": 7.93,
+      "grad_norm": 0.06150615215301514,
+      "learning_rate": 9.422832443427409e-05,
+      "loss": 0.0162,
+      "step": 52000
+    },
+    {
+      "epoch": 8.0,
+      "eval_execution_accuracy": 65.8607,
+      "eval_loss": 0.0669085830450058,
+      "eval_runtime": 1870.6797,
+      "eval_samples_per_second": 0.553,
+      "eval_steps_per_second": 0.069,
+      "step": 52440
+    },
+    {
+      "epoch": 8.01,
+      "grad_norm": 0.3560275733470917,
+      "learning_rate": 9.321128909229596e-05,
+      "loss": 0.0137,
+      "step": 52500
+    },
+    {
+      "epoch": 8.09,
+      "grad_norm": 0.0782669186592102,
+      "learning_rate": 9.219425375031783e-05,
+      "loss": 0.0114,
+      "step": 53000
+    },
+    {
+      "epoch": 8.16,
+      "grad_norm": 0.008491788990795612,
+      "learning_rate": 9.11772184083397e-05,
+      "loss": 0.0124,
+      "step": 53500
+    },
+    {
+      "epoch": 8.24,
+      "grad_norm": 0.1824067234992981,
+      "learning_rate": 9.016018306636155e-05,
+      "loss": 0.0122,
+      "step": 54000
+    },
+    {
+      "epoch": 8.31,
+      "grad_norm": 0.1216733381152153,
+      "learning_rate": 8.914314772438342e-05,
+      "loss": 0.0124,
+      "step": 54500
+    },
+    {
+      "epoch": 8.39,
+      "grad_norm": 0.4382436275482178,
+      "learning_rate": 8.812611238240529e-05,
+      "loss": 0.0115,
+      "step": 55000
+    },
+    {
+      "epoch": 8.47,
+      "grad_norm": 0.35070136189460754,
+      "learning_rate": 8.710907704042716e-05,
+      "loss": 0.0111,
+      "step": 55500
+    },
+    {
+      "epoch": 8.54,
+      "grad_norm": 0.03633696213364601,
+      "learning_rate": 8.609204169844902e-05,
+      "loss": 0.0111,
+      "step": 56000
+    },
+    {
+      "epoch": 8.62,
+      "grad_norm": 0.05109800025820732,
+      "learning_rate": 8.507500635647089e-05,
+      "loss": 0.0129,
+      "step": 56500
+    },
+    {
+      "epoch": 8.7,
+      "grad_norm": 0.02394057996571064,
+      "learning_rate": 8.405797101449276e-05,
+      "loss": 0.012,
+      "step": 57000
+    },
+    {
+      "epoch": 8.77,
+      "grad_norm": 0.5572072863578796,
+      "learning_rate": 8.304093567251462e-05,
+      "loss": 0.0121,
+      "step": 57500
+    },
+    {
+      "epoch": 8.85,
+      "grad_norm": 0.10420696437358856,
+      "learning_rate": 8.202390033053648e-05,
+      "loss": 0.0113,
+      "step": 58000
+    },
+    {
+      "epoch": 8.92,
+      "grad_norm": 0.14662973582744598,
+      "learning_rate": 8.100686498855835e-05,
+      "loss": 0.0109,
+      "step": 58500
+    },
+    {
+      "epoch": 9.0,
+      "eval_execution_accuracy": 68.9555,
+      "eval_loss": 0.06655910611152649,
+      "eval_runtime": 1868.1909,
+      "eval_samples_per_second": 0.553,
+      "eval_steps_per_second": 0.07,
+      "step": 58995
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.44341155886650085,
+      "learning_rate": 7.998982964658023e-05,
+      "loss": 0.0117,
+      "step": 59000
+    },
+    {
+      "epoch": 9.08,
+      "grad_norm": 0.07052640616893768,
+      "learning_rate": 7.897279430460209e-05,
+      "loss": 0.0109,
+      "step": 59500
+    },
+    {
+      "epoch": 9.15,
+      "grad_norm": 0.22480645775794983,
+      "learning_rate": 7.795575896262396e-05,
+      "loss": 0.0095,
+      "step": 60000
+    },
+    {
+      "epoch": 9.23,
+      "grad_norm": 0.3521146774291992,
+      "learning_rate": 7.693872362064583e-05,
+      "loss": 0.0105,
+      "step": 60500
+    },
+    {
+      "epoch": 9.31,
+      "grad_norm": 0.17205676436424255,
+      "learning_rate": 7.59216882786677e-05,
+      "loss": 0.0099,
+      "step": 61000
+    },
+    {
+      "epoch": 9.38,
+      "grad_norm": 0.018218664452433586,
+      "learning_rate": 7.490465293668955e-05,
+      "loss": 0.01,
+      "step": 61500
+    },
+    {
+      "epoch": 9.46,
+      "grad_norm": 0.0007620451506227255,
+      "learning_rate": 7.388761759471142e-05,
+      "loss": 0.0097,
+      "step": 62000
+    },
+    {
+      "epoch": 9.53,
+      "grad_norm": 0.12471388280391693,
+      "learning_rate": 7.287058225273329e-05,
+      "loss": 0.0102,
+      "step": 62500
+    },
+    {
+      "epoch": 9.61,
+      "grad_norm": 0.0011848780559375882,
+      "learning_rate": 7.185354691075516e-05,
+      "loss": 0.0093,
+      "step": 63000
+    },
+    {
+      "epoch": 9.69,
+      "grad_norm": 0.32076504826545715,
+      "learning_rate": 7.083651156877702e-05,
+      "loss": 0.0096,
+      "step": 63500
+    },
+    {
+      "epoch": 9.76,
+      "grad_norm": 1.0963212251663208,
+      "learning_rate": 6.981947622679888e-05,
+      "loss": 0.0103,
+      "step": 64000
+    },
+    {
+      "epoch": 9.84,
+      "grad_norm": 0.2559475004673004,
+      "learning_rate": 6.880244088482075e-05,
+      "loss": 0.011,
+      "step": 64500
+    },
+    {
+      "epoch": 9.92,
+      "grad_norm": 0.1217416375875473,
+      "learning_rate": 6.778540554284262e-05,
+      "loss": 0.0092,
+      "step": 65000
+    },
+    {
+      "epoch": 9.99,
+      "grad_norm": 0.004103431012481451,
+      "learning_rate": 6.676837020086448e-05,
+      "loss": 0.0101,
+      "step": 65500
+    },
+    {
+      "epoch": 10.0,
+      "eval_execution_accuracy": 68.1818,
+      "eval_loss": 0.07360666990280151,
+      "eval_runtime": 1900.7634,
+      "eval_samples_per_second": 0.544,
+      "eval_steps_per_second": 0.068,
+      "step": 65550
+    },
+    {
+      "epoch": 10.07,
+      "grad_norm": 0.13344629108905792,
+      "learning_rate": 6.575133485888635e-05,
+      "loss": 0.0092,
+      "step": 66000
+    },
+    {
+      "epoch": 10.14,
+      "grad_norm": 0.0032061520032584667,
+      "learning_rate": 6.473429951690822e-05,
+      "loss": 0.0081,
+      "step": 66500
+    },
+    {
+      "epoch": 10.22,
+      "grad_norm": 0.21120476722717285,
+      "learning_rate": 6.371726417493009e-05,
+      "loss": 0.0086,
+      "step": 67000
+    },
+    {
+      "epoch": 10.3,
+      "grad_norm": 0.00848371535539627,
+      "learning_rate": 6.270022883295194e-05,
+      "loss": 0.0081,
+      "step": 67500
+    },
+    {
+      "epoch": 10.37,
+      "grad_norm": 0.0012110616080462933,
+      "learning_rate": 6.168319349097381e-05,
+      "loss": 0.0085,
+      "step": 68000
+    },
+    {
+      "epoch": 10.45,
+      "grad_norm": 0.05799203738570213,
+      "learning_rate": 6.066615814899568e-05,
+      "loss": 0.0078,
+      "step": 68500
+    },
+    {
+      "epoch": 10.53,
+      "grad_norm": 0.03763442113995552,
+      "learning_rate": 5.9649122807017544e-05,
+      "loss": 0.008,
+      "step": 69000
+    },
+    {
+      "epoch": 10.6,
+      "grad_norm": 0.01833200454711914,
+      "learning_rate": 5.8632087465039406e-05,
+      "loss": 0.0089,
+      "step": 69500
+    },
+    {
+      "epoch": 10.68,
+      "grad_norm": 0.27255308628082275,
+      "learning_rate": 5.7615052123061275e-05,
+      "loss": 0.0085,
+      "step": 70000
+    },
+    {
+      "epoch": 10.76,
+      "grad_norm": 0.049906667321920395,
+      "learning_rate": 5.659801678108314e-05,
+      "loss": 0.0093,
+      "step": 70500
+    },
+    {
+      "epoch": 10.83,
+      "grad_norm": 0.49261561036109924,
+      "learning_rate": 5.558098143910501e-05,
+      "loss": 0.0099,
+      "step": 71000
+    },
+    {
+      "epoch": 10.91,
+      "grad_norm": 0.010688086971640587,
+      "learning_rate": 5.456394609712687e-05,
+      "loss": 0.0092,
+      "step": 71500
+    },
+    {
+      "epoch": 10.98,
+      "grad_norm": 0.015557405538856983,
+      "learning_rate": 5.354691075514875e-05,
+      "loss": 0.0085,
+      "step": 72000
+    },
+    {
+      "epoch": 11.0,
+      "eval_execution_accuracy": 68.0851,
+      "eval_loss": 0.07639693468809128,
+      "eval_runtime": 1996.6932,
+      "eval_samples_per_second": 0.518,
+      "eval_steps_per_second": 0.065,
+      "step": 72105
+    },
+    {
+      "epoch": 11.06,
+      "grad_norm": 0.1298118531703949,
+      "learning_rate": 5.2529875413170615e-05,
+      "loss": 0.0078,
+      "step": 72500
+    },
+    {
+      "epoch": 11.14,
+      "grad_norm": 0.08524327725172043,
+      "learning_rate": 5.151284007119248e-05,
+      "loss": 0.0085,
+      "step": 73000
+    },
+    {
+      "epoch": 11.21,
+      "grad_norm": 0.1634071171283722,
+      "learning_rate": 5.049580472921435e-05,
+      "loss": 0.0071,
+      "step": 73500
+    },
+    {
+      "epoch": 11.29,
+      "grad_norm": 0.0011399647919461131,
+      "learning_rate": 4.947876938723621e-05,
+      "loss": 0.0069,
+      "step": 74000
+    },
+    {
+      "epoch": 11.37,
+      "grad_norm": 0.010579722002148628,
+      "learning_rate": 4.846173404525807e-05,
+      "loss": 0.0072,
+      "step": 74500
+    },
+    {
+      "epoch": 11.44,
+      "grad_norm": 0.014801290817558765,
+      "learning_rate": 4.744469870327994e-05,
+      "loss": 0.0067,
+      "step": 75000
+    },
+    {
+      "epoch": 11.52,
+      "grad_norm": 0.0037248600274324417,
+      "learning_rate": 4.642766336130181e-05,
+      "loss": 0.0075,
+      "step": 75500
+    },
+    {
+      "epoch": 11.59,
+      "grad_norm": 0.00024146214127540588,
+      "learning_rate": 4.541062801932367e-05,
+      "loss": 0.0065,
+      "step": 76000
+    },
+    {
+      "epoch": 11.67,
+      "grad_norm": 0.013673787005245686,
+      "learning_rate": 4.439359267734554e-05,
+      "loss": 0.0071,
+      "step": 76500
+    },
+    {
+      "epoch": 11.75,
+      "grad_norm": 0.4386146366596222,
+      "learning_rate": 4.3376557335367405e-05,
+      "loss": 0.0073,
+      "step": 77000
+    },
+    {
+      "epoch": 11.82,
+      "grad_norm": 0.011454693973064423,
+      "learning_rate": 4.2359521993389274e-05,
+      "loss": 0.0071,
+      "step": 77500
+    },
+    {
+      "epoch": 11.9,
+      "grad_norm": 0.2784646451473236,
+      "learning_rate": 4.1342486651411136e-05,
+      "loss": 0.0084,
+      "step": 78000
+    },
+    {
+      "epoch": 11.98,
+      "grad_norm": 0.1163712665438652,
+      "learning_rate": 4.0325451309433006e-05,
+      "loss": 0.0069,
+      "step": 78500
+    },
+    {
+      "epoch": 12.0,
+      "eval_execution_accuracy": 69.0522,
+      "eval_loss": 0.08005601912736893,
+      "eval_runtime": 1886.3805,
+      "eval_samples_per_second": 0.548,
+      "eval_steps_per_second": 0.069,
+      "step": 78660
+    },
+    {
+      "epoch": 12.05,
+      "grad_norm": 0.41248416900634766,
+      "learning_rate": 3.930841596745487e-05,
+      "loss": 0.007,
+      "step": 79000
+    },
+    {
+      "epoch": 12.13,
+      "grad_norm": 0.38738590478897095,
+      "learning_rate": 3.829138062547674e-05,
+      "loss": 0.0069,
+      "step": 79500
+    },
+    {
+      "epoch": 12.2,
+      "grad_norm": 0.24087974429130554,
+      "learning_rate": 3.72743452834986e-05,
+      "loss": 0.0057,
+      "step": 80000
+    },
+    {
+      "epoch": 12.28,
+      "grad_norm": 0.18917705118656158,
+      "learning_rate": 3.625730994152047e-05,
+      "loss": 0.0065,
+      "step": 80500
+    },
+    {
+      "epoch": 12.36,
+      "grad_norm": 0.05060713738203049,
+      "learning_rate": 3.524027459954233e-05,
+      "loss": 0.0054,
+      "step": 81000
+    },
+    {
+      "epoch": 12.43,
+      "grad_norm": 0.07384895533323288,
+      "learning_rate": 3.422323925756421e-05,
+      "loss": 0.0063,
+      "step": 81500
+    },
+    {
+      "epoch": 12.51,
+      "grad_norm": 0.22887946665287018,
+      "learning_rate": 3.320620391558607e-05,
+      "loss": 0.0057,
+      "step": 82000
+    },
+    {
+      "epoch": 12.59,
+      "grad_norm": 0.2123759686946869,
+      "learning_rate": 3.218916857360794e-05,
+      "loss": 0.0074,
+      "step": 82500
+    },
+    {
+      "epoch": 12.66,
+      "grad_norm": 0.09510879218578339,
+      "learning_rate": 3.11721332316298e-05,
+      "loss": 0.0056,
+      "step": 83000
+    },
+    {
+      "epoch": 12.74,
+      "grad_norm": 0.00010326172196073458,
+      "learning_rate": 3.0155097889651668e-05,
+      "loss": 0.0058,
+      "step": 83500
+    },
+    {
+      "epoch": 12.81,
+      "grad_norm": 0.37206101417541504,
+      "learning_rate": 2.9138062547673534e-05,
+      "loss": 0.0059,
+      "step": 84000
+    },
+    {
+      "epoch": 12.89,
+      "grad_norm": 0.10882502794265747,
+      "learning_rate": 2.81210272056954e-05,
+      "loss": 0.0053,
+      "step": 84500
+    },
+    {
+      "epoch": 12.97,
+      "grad_norm": 0.010751358233392239,
+      "learning_rate": 2.7103991863717266e-05,
+      "loss": 0.0068,
+      "step": 85000
+    },
+    {
+      "epoch": 13.0,
+      "eval_execution_accuracy": 69.2456,
+      "eval_loss": 0.0884392261505127,
+      "eval_runtime": 1938.7518,
+      "eval_samples_per_second": 0.533,
+      "eval_steps_per_second": 0.067,
+      "step": 85215
+    },
+    {
+      "epoch": 13.04,
+      "grad_norm": 0.10975372046232224,
+      "learning_rate": 2.608695652173913e-05,
+      "loss": 0.0057,
+      "step": 85500
+    },
+    {
+      "epoch": 13.12,
+      "grad_norm": 0.0004275761893950403,
+      "learning_rate": 2.5069921179760997e-05,
+      "loss": 0.0048,
+      "step": 86000
+    },
+    {
+      "epoch": 13.2,
+      "grad_norm": 0.3996267020702362,
+      "learning_rate": 2.4052885837782867e-05,
+      "loss": 0.0051,
+      "step": 86500
+    },
+    {
+      "epoch": 13.27,
+      "grad_norm": 0.00662227114662528,
+      "learning_rate": 2.3035850495804733e-05,
+      "loss": 0.0062,
+      "step": 87000
+    },
+    {
+      "epoch": 13.35,
+      "grad_norm": 0.09702113270759583,
+      "learning_rate": 2.20188151538266e-05,
+      "loss": 0.0051,
+      "step": 87500
+    },
+    {
+      "epoch": 13.42,
+      "grad_norm": 0.0026878053322434425,
+      "learning_rate": 2.100177981184846e-05,
+      "loss": 0.0063,
+      "step": 88000
+    },
+    {
+      "epoch": 13.5,
+      "grad_norm": 0.05382531136274338,
+      "learning_rate": 1.9984744469870327e-05,
+      "loss": 0.0042,
+      "step": 88500
+    },
+    {
+      "epoch": 13.58,
+      "grad_norm": 0.770341157913208,
+      "learning_rate": 1.8967709127892193e-05,
+      "loss": 0.0052,
+      "step": 89000
+    },
+    {
+      "epoch": 13.65,
+      "grad_norm": 0.00518847955390811,
+      "learning_rate": 1.795067378591406e-05,
+      "loss": 0.0052,
+      "step": 89500
+    },
+    {
+      "epoch": 13.73,
+      "grad_norm": 0.0707794651389122,
+      "learning_rate": 1.6933638443935928e-05,
+      "loss": 0.0053,
+      "step": 90000
+    },
+    {
+      "epoch": 13.81,
+      "grad_norm": 0.5020930767059326,
+      "learning_rate": 1.5916603101957794e-05,
+      "loss": 0.0057,
+      "step": 90500
+    },
+    {
+      "epoch": 13.88,
+      "grad_norm": 0.11777380853891373,
+      "learning_rate": 1.489956775997966e-05,
+      "loss": 0.0056,
+      "step": 91000
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 0.0008695057476870716,
+      "learning_rate": 1.3882532418001526e-05,
+      "loss": 0.0052,
+      "step": 91500
+    },
+    {
+      "epoch": 14.0,
+      "eval_execution_accuracy": 70.793,
+      "eval_loss": 0.08826606720685959,
+      "eval_runtime": 1858.3154,
+      "eval_samples_per_second": 0.556,
+      "eval_steps_per_second": 0.07,
+      "step": 91770
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 98325,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "total_flos": 8.553259153863475e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53b752b7955d88fc1560b2874e9682406268f9709db3ff80517479dd3f6a2edb
+oid sha256:dede708255d17950cd0ceacfc76f91fd3379b42a34bfdc561353a82976b8fcf6
 size 5112