End of training

README.md

@@ -3,11 +3,23 @@ library_name: transformers
 base_model: microsoft/codebert-base-mlm
 tags:
 - generated_from_trainer
+datasets:
+- devgpt-aimotion/the-stack-v2_PlantUML_filtered
 metrics:
 - accuracy
 model-index:
 - name: codebert_base_code_uml_c
-  results: []
+  results:
+  - task:
+      name: Masked Language Modeling
+      type: fill-mask
+    dataset:
+      name: devgpt-aimotion/the-stack-v2_PlantUML_filtered
+      type: devgpt-aimotion/the-stack-v2_PlantUML_filtered
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9053223443951083
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,9 +27,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # codebert_base_code_uml_c
 
-This model is a fine-tuned version of [microsoft/codebert-base-mlm](https://huggingface.co/microsoft/codebert-base-mlm) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/codebert-base-mlm](https://huggingface.co/microsoft/codebert-base-mlm) on the devgpt-aimotion/the-stack-v2_PlantUML_filtered dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4521
+- Loss: 0.4533
 - Accuracy: 0.9053
 
 ## Model description

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9053223443951083,
+    "eval_loss": 0.45334097743034363,
+    "eval_runtime": 83.1276,
+    "eval_samples": 12451,
+    "eval_samples_per_second": 149.782,
+    "eval_steps_per_second": 1.564,
+    "perplexity": 1.573560643713862,
+    "total_flos": 2.898276322152499e+17,
+    "train_loss": 0.5986486167209296,
+    "train_runtime": 10447.1842,
+    "train_samples": 220179,
+    "train_samples_per_second": 105.377,
+    "train_steps_per_second": 1.098
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9053223443951083,
+    "eval_loss": 0.45334097743034363,
+    "eval_runtime": 83.1276,
+    "eval_samples": 12451,
+    "eval_samples_per_second": 149.782,
+    "eval_steps_per_second": 1.564,
+    "perplexity": 1.573560643713862
+}

logs/events.out.tfevents.1750868233.ki-g0008.1157710.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d04d3ce367532a850ca5130929333786ee7cae7de556630a64c013c35cebd1
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 2.898276322152499e+17,
+    "train_loss": 0.5986486167209296,
+    "train_runtime": 10447.1842,
+    "train_samples": 220179,
+    "train_samples_per_second": 105.377,
+    "train_steps_per_second": 1.098
+}

trainer_state.json

@@ -0,0 +1,206 @@
+{
+  "best_global_step": 10000,
+  "best_metric": 0.45208191871643066,
+  "best_model_checkpoint": "codebert_base_code_uml_c/checkpoint-10000",
+  "epoch": 5.0,
+  "eval_steps": 10000,
+  "global_step": 11470,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21795989537925023,
+      "grad_norm": 1.2200626134872437,
+      "learning_rate": 4.9900000000000005e-06,
+      "loss": 0.9993,
+      "step": 500
+    },
+    {
+      "epoch": 0.43591979075850046,
+      "grad_norm": 1.1631908416748047,
+      "learning_rate": 9.990000000000001e-06,
+      "loss": 0.767,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6538796861377506,
+      "grad_norm": 0.973538339138031,
+      "learning_rate": 1.499e-05,
+      "loss": 0.7035,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8718395815170009,
+      "grad_norm": 0.8392261862754822,
+      "learning_rate": 1.999e-05,
+      "loss": 0.6682,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0897994768962511,
+      "grad_norm": 0.8580324053764343,
+      "learning_rate": 2.4990000000000003e-05,
+      "loss": 0.6422,
+      "step": 2500
+    },
+    {
+      "epoch": 1.3077593722755014,
+      "grad_norm": 0.911376416683197,
+      "learning_rate": 2.9990000000000003e-05,
+      "loss": 0.6221,
+      "step": 3000
+    },
+    {
+      "epoch": 1.5257192676547515,
+      "grad_norm": 0.821864902973175,
+      "learning_rate": 3.499e-05,
+      "loss": 0.6094,
+      "step": 3500
+    },
+    {
+      "epoch": 1.7436791630340016,
+      "grad_norm": 0.8506414890289307,
+      "learning_rate": 3.999e-05,
+      "loss": 0.5945,
+      "step": 4000
+    },
+    {
+      "epoch": 1.961639058413252,
+      "grad_norm": 0.7997013330459595,
+      "learning_rate": 4.499e-05,
+      "loss": 0.5884,
+      "step": 4500
+    },
+    {
+      "epoch": 2.1795989537925022,
+      "grad_norm": 0.8773174285888672,
+      "learning_rate": 4.999e-05,
+      "loss": 0.5753,
+      "step": 5000
+    },
+    {
+      "epoch": 2.3975588491717525,
+      "grad_norm": 0.7826923131942749,
+      "learning_rate": 5.499000000000001e-05,
+      "loss": 0.5712,
+      "step": 5500
+    },
+    {
+      "epoch": 2.615518744551003,
+      "grad_norm": 0.7175124287605286,
+      "learning_rate": 5.999e-05,
+      "loss": 0.5602,
+      "step": 6000
+    },
+    {
+      "epoch": 2.8334786399302527,
+      "grad_norm": 0.6982043981552124,
+      "learning_rate": 6.499000000000001e-05,
+      "loss": 0.5554,
+      "step": 6500
+    },
+    {
+      "epoch": 3.051438535309503,
+      "grad_norm": 0.6505544781684875,
+      "learning_rate": 6.999e-05,
+      "loss": 0.5491,
+      "step": 7000
+    },
+    {
+      "epoch": 3.2693984306887534,
+      "grad_norm": 0.7241908311843872,
+      "learning_rate": 7.499e-05,
+      "loss": 0.5435,
+      "step": 7500
+    },
+    {
+      "epoch": 3.4873583260680037,
+      "grad_norm": 0.7068212032318115,
+      "learning_rate": 7.999000000000001e-05,
+      "loss": 0.5433,
+      "step": 8000
+    },
+    {
+      "epoch": 3.7053182214472535,
+      "grad_norm": 0.7010810375213623,
+      "learning_rate": 8.499e-05,
+      "loss": 0.5385,
+      "step": 8500
+    },
+    {
+      "epoch": 3.923278116826504,
+      "grad_norm": 0.685562252998352,
+      "learning_rate": 8.999000000000001e-05,
+      "loss": 0.534,
+      "step": 9000
+    },
+    {
+      "epoch": 4.141238012205754,
+      "grad_norm": 0.700875997543335,
+      "learning_rate": 9.499e-05,
+      "loss": 0.5343,
+      "step": 9500
+    },
+    {
+      "epoch": 4.3591979075850045,
+      "grad_norm": 0.7298157811164856,
+      "learning_rate": 9.999000000000001e-05,
+      "loss": 0.5254,
+      "step": 10000
+    },
+    {
+      "epoch": 4.3591979075850045,
+      "eval_accuracy": 0.9053344805784795,
+      "eval_loss": 0.45208191871643066,
+      "eval_runtime": 83.4945,
+      "eval_samples_per_second": 149.124,
+      "eval_steps_per_second": 1.557,
+      "step": 10000
+    },
+    {
+      "epoch": 4.577157802964255,
+      "grad_norm": 0.677169680595398,
+      "learning_rate": 6.605442176870749e-05,
+      "loss": 0.5214,
+      "step": 10500
+    },
+    {
+      "epoch": 4.795117698343505,
+      "grad_norm": 0.7635814547538757,
+      "learning_rate": 3.2040816326530615e-05,
+      "loss": 0.5126,
+      "step": 11000
+    },
+    {
+      "epoch": 5.0,
+      "step": 11470,
+      "total_flos": 2.898276322152499e+17,
+      "train_loss": 0.5986486167209296,
+      "train_runtime": 10447.1842,
+      "train_samples_per_second": 105.377,
+      "train_steps_per_second": 1.098
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 11470,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.898276322152499e+17,
+  "train_batch_size": 96,
+  "trial_name": null,
+  "trial_params": null
+}