End of training

README.md

@@ -1,11 +1,27 @@
 ---
+language:
+- en
 license: bsd-3-clause
 base_model: Salesforce/codet5p-220m
 tags:
 - generated_from_trainer
+datasets:
+- juraj-juraj/python_googlestyle_docstrings
+metrics:
+- bleu
 model-index:
 - name: t5_codet5p_220m_tuned
-  results: []
+  results:
+  - task:
+      name: Translation
+      type: translation
+    dataset:
+      name: juraj-juraj/python_googlestyle_docstrings
+      type: juraj-juraj/python_googlestyle_docstrings
+    metrics:
+    - name: Bleu
+      type: bleu
+      value: 19.7909
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,7 +29,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # t5_codet5p_220m_tuned
 
-This model is a fine-tuned version of [Salesforce/codet5p-220m](https://huggingface.co/Salesforce/codet5p-220m) on an unknown dataset.
+This model is a fine-tuned version of [Salesforce/codet5p-220m](https://huggingface.co/Salesforce/codet5p-220m) on the juraj-juraj/python_googlestyle_docstrings dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6467
+- Bleu: 19.7909
+- Gen Len: 54.518
 
 ## Model description
 

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 2.0,
+    "eval_bleu": 19.7909,
+    "eval_gen_len": 54.518,
+    "eval_loss": 1.6466972827911377,
+    "eval_runtime": 437.9521,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 2.283,
+    "eval_steps_per_second": 0.571,
+    "predict_bleu": 17.8409,
+    "predict_gen_len": 62.072,
+    "predict_loss": 1.6726146936416626,
+    "predict_runtime": 483.4666,
+    "predict_samples": 1000,
+    "predict_samples_per_second": 2.068,
+    "predict_steps_per_second": 0.517,
+    "train_loss": 1.6027834024951335,
+    "train_runtime": 7360.333,
+    "train_samples": 27895,
+    "train_samples_per_second": 7.58,
+    "train_steps_per_second": 2.527
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 2.0,
+    "eval_bleu": 19.7909,
+    "eval_gen_len": 54.518,
+    "eval_loss": 1.6466972827911377,
+    "eval_runtime": 437.9521,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 2.283,
+    "eval_steps_per_second": 0.571
+}

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 1,
   "decoder_start_token_id": 0,
   "eos_token_id": 2,

predict_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_bleu": 17.8409,
+    "predict_gen_len": 62.072,
+    "predict_loss": 1.6726146936416626,
+    "predict_runtime": 483.4666,
+    "predict_samples": 1000,
+    "predict_samples_per_second": 2.068,
+    "predict_steps_per_second": 0.517
+}

runs/Feb09_15-49-15_a6a943090935/events.out.tfevents.1707501655.a6a943090935.1982.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb8860592d8b702344ec81a92c193d8df7caf98292e63e968d1450280138c124
+size 465

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 1.6027834024951335,
+    "train_runtime": 7360.333,
+    "train_samples": 27895,
+    "train_samples_per_second": 7.58,
+    "train_steps_per_second": 2.527
+}

trainer_state.json

@@ -0,0 +1,250 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 18598,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.731153887514787e-06,
+      "loss": 1.8656,
+      "step": 500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.462307775029573e-06,
+      "loss": 1.8079,
+      "step": 1000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.193461662544361e-06,
+      "loss": 1.7757,
+      "step": 1500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 8.924615550059147e-06,
+      "loss": 1.7549,
+      "step": 2000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 8.655769437573934e-06,
+      "loss": 1.7183,
+      "step": 2500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 8.38692332508872e-06,
+      "loss": 1.7325,
+      "step": 3000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 8.118077212603506e-06,
+      "loss": 1.7002,
+      "step": 3500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 7.849231100118292e-06,
+      "loss": 1.7217,
+      "step": 4000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.580384987633079e-06,
+      "loss": 1.7195,
+      "step": 4500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 7.311538875147866e-06,
+      "loss": 1.6911,
+      "step": 5000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.042692762662653e-06,
+      "loss": 1.6482,
+      "step": 5500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 6.773846650177439e-06,
+      "loss": 1.6911,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.505000537692225e-06,
+      "loss": 1.6361,
+      "step": 6500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 6.236154425207011e-06,
+      "loss": 1.6181,
+      "step": 7000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 5.967308312721799e-06,
+      "loss": 1.6496,
+      "step": 7500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 5.6984622002365855e-06,
+      "loss": 1.6331,
+      "step": 8000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.429616087751372e-06,
+      "loss": 1.6057,
+      "step": 8500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.160769975266158e-06,
+      "loss": 1.6225,
+      "step": 9000
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 4.891923862780945e-06,
+      "loss": 1.5955,
+      "step": 9500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 4.623077750295731e-06,
+      "loss": 1.528,
+      "step": 10000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 4.354231637810517e-06,
+      "loss": 1.5348,
+      "step": 10500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 4.085385525325304e-06,
+      "loss": 1.5142,
+      "step": 11000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 3.816539412840091e-06,
+      "loss": 1.4924,
+      "step": 11500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 3.547693300354877e-06,
+      "loss": 1.5045,
+      "step": 12000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 3.2788471878696636e-06,
+      "loss": 1.4959,
+      "step": 12500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 3.01000107538445e-06,
+      "loss": 1.5248,
+      "step": 13000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2.741154962899237e-06,
+      "loss": 1.4984,
+      "step": 13500
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.4723088504140235e-06,
+      "loss": 1.5079,
+      "step": 14000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.2034627379288097e-06,
+      "loss": 1.5105,
+      "step": 14500
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.9346166254435964e-06,
+      "loss": 1.5058,
+      "step": 15000
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.6657705129583828e-06,
+      "loss": 1.4941,
+      "step": 15500
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.3969244004731695e-06,
+      "loss": 1.5275,
+      "step": 16000
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.1280782879879559e-06,
+      "loss": 1.5091,
+      "step": 16500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 8.592321755027423e-07,
+      "loss": 1.4995,
+      "step": 17000
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 5.903860630175289e-07,
+      "loss": 1.5139,
+      "step": 17500
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 3.215399505323153e-07,
+      "loss": 1.4951,
+      "step": 18000
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.2693838047101844e-08,
+      "loss": 1.478,
+      "step": 18500
+    },
+    {
+      "epoch": 2.0,
+      "step": 18598,
+      "total_flos": 2.094047285686272e+16,
+      "train_loss": 1.6027834024951335,
+      "train_runtime": 7360.333,
+      "train_samples_per_second": 7.58,
+      "train_steps_per_second": 2.527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 18598,
+  "num_train_epochs": 2,
+  "save_steps": 4000,
+  "total_flos": 2.094047285686272e+16,
+  "trial_name": null,
+  "trial_params": null
+}