End of training

README.md

@@ -4,9 +4,23 @@ license: apache-2.0
 base_model: facebook/bart-large
 tags:
 - generated_from_trainer
+datasets:
+- Mwnthai/bodo-legal-summary-data
+metrics:
+- accuracy
 model-index:
 - name: bart-base-bodo
-  results: []
+  results:
+  - task:
+      name: Masked Language Modeling
+      type: fill-mask
+    dataset:
+      name: Mwnthai/bodo-legal-summary-data
+      type: Mwnthai/bodo-legal-summary-data
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.04001446442091465
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,7 +28,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bart-base-bodo
 
-This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
+This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the Mwnthai/bodo-legal-summary-data dataset.
+It achieves the following results on the evaluation set:
+- Loss: 7.4122
+- Accuracy: 0.0400
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.04001446442091465,
+    "eval_loss": 7.412208080291748,
+    "eval_runtime": 76.853,
+    "eval_samples": 578,
+    "eval_samples_per_second": 7.521,
+    "eval_steps_per_second": 3.76,
+    "perplexity": 1656.0790681814292,
+    "total_flos": 1.2851147000984371e+17,
+    "train_loss": 7.479052871051595,
+    "train_runtime": 34661.0306,
+    "train_samples": 19767,
+    "train_samples_per_second": 1.711,
+    "train_steps_per_second": 0.855
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.04001446442091465,
+    "eval_loss": 7.412208080291748,
+    "eval_runtime": 76.853,
+    "eval_samples": 578,
+    "eval_samples_per_second": 7.521,
+    "eval_steps_per_second": 3.76,
+    "perplexity": 1656.0790681814292
+}

runs/Feb24_23-11-51_gitspot/events.out.tfevents.1740453904.gitspot.2290460.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e0d608c5cbf4e2707b7758cf580faa503eef3cfb6de6b4d61177a4a9df2ec9
+size 369

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.2851147000984371e+17,
+    "train_loss": 7.479052871051595,
+    "train_runtime": 34661.0306,
+    "train_samples": 19767,
+    "train_samples_per_second": 1.711,
+    "train_steps_per_second": 0.855
+}

trainer_state.json

@@ -0,0 +1,455 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 5000.0,
+  "global_step": 29652,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.050586806960744635,
+      "grad_norm": 3.026057720184326,
+      "learning_rate": 4.9156886550654254e-05,
+      "loss": 7.7479,
+      "step": 500
+    },
+    {
+      "epoch": 0.10117361392148927,
+      "grad_norm": 2.428532361984253,
+      "learning_rate": 4.831377310130851e-05,
+      "loss": 7.602,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1517604208822339,
+      "grad_norm": 3.12160587310791,
+      "learning_rate": 4.7470659651962764e-05,
+      "loss": 7.5609,
+      "step": 1500
+    },
+    {
+      "epoch": 0.20234722784297854,
+      "grad_norm": 2.7097604274749756,
+      "learning_rate": 4.662754620261703e-05,
+      "loss": 7.5615,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2529340348037232,
+      "grad_norm": 2.684849500656128,
+      "learning_rate": 4.578443275327128e-05,
+      "loss": 7.5591,
+      "step": 2500
+    },
+    {
+      "epoch": 0.3035208417644678,
+      "grad_norm": 2.7275538444519043,
+      "learning_rate": 4.494131930392554e-05,
+      "loss": 7.5242,
+      "step": 3000
+    },
+    {
+      "epoch": 0.35410764872521244,
+      "grad_norm": 3.8471314907073975,
+      "learning_rate": 4.409820585457979e-05,
+      "loss": 7.5216,
+      "step": 3500
+    },
+    {
+      "epoch": 0.4046944556859571,
+      "grad_norm": 3.268939971923828,
+      "learning_rate": 4.325509240523405e-05,
+      "loss": 7.5121,
+      "step": 4000
+    },
+    {
+      "epoch": 0.45528126264670177,
+      "grad_norm": 4.609728813171387,
+      "learning_rate": 4.24119789558883e-05,
+      "loss": 7.4998,
+      "step": 4500
+    },
+    {
+      "epoch": 0.5058680696074463,
+      "grad_norm": 3.0856144428253174,
+      "learning_rate": 4.156886550654257e-05,
+      "loss": 7.4945,
+      "step": 5000
+    },
+    {
+      "epoch": 0.556454876568191,
+      "grad_norm": 3.188549757003784,
+      "learning_rate": 4.072575205719682e-05,
+      "loss": 7.4944,
+      "step": 5500
+    },
+    {
+      "epoch": 0.6070416835289356,
+      "grad_norm": 3.380218982696533,
+      "learning_rate": 3.988263860785108e-05,
+      "loss": 7.5203,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6576284904896803,
+      "grad_norm": 3.2636780738830566,
+      "learning_rate": 3.903952515850533e-05,
+      "loss": 7.4899,
+      "step": 6500
+    },
+    {
+      "epoch": 0.7082152974504249,
+      "grad_norm": 3.4519433975219727,
+      "learning_rate": 3.819641170915959e-05,
+      "loss": 7.4763,
+      "step": 7000
+    },
+    {
+      "epoch": 0.7588021044111696,
+      "grad_norm": 3.5375866889953613,
+      "learning_rate": 3.735329825981384e-05,
+      "loss": 7.4911,
+      "step": 7500
+    },
+    {
+      "epoch": 0.8093889113719142,
+      "grad_norm": 3.090251922607422,
+      "learning_rate": 3.65101848104681e-05,
+      "loss": 7.4606,
+      "step": 8000
+    },
+    {
+      "epoch": 0.8599757183326588,
+      "grad_norm": 2.6117258071899414,
+      "learning_rate": 3.5667071361122356e-05,
+      "loss": 7.4925,
+      "step": 8500
+    },
+    {
+      "epoch": 0.9105625252934035,
+      "grad_norm": 3.3298494815826416,
+      "learning_rate": 3.482395791177661e-05,
+      "loss": 7.4626,
+      "step": 9000
+    },
+    {
+      "epoch": 0.9611493322541481,
+      "grad_norm": 3.267622232437134,
+      "learning_rate": 3.398084446243087e-05,
+      "loss": 7.4583,
+      "step": 9500
+    },
+    {
+      "epoch": 1.0117361392148927,
+      "grad_norm": 3.9384641647338867,
+      "learning_rate": 3.313773101308512e-05,
+      "loss": 7.471,
+      "step": 10000
+    },
+    {
+      "epoch": 1.0623229461756374,
+      "grad_norm": 3.3493237495422363,
+      "learning_rate": 3.229461756373938e-05,
+      "loss": 7.4833,
+      "step": 10500
+    },
+    {
+      "epoch": 1.112909753136382,
+      "grad_norm": 4.062368869781494,
+      "learning_rate": 3.145150411439363e-05,
+      "loss": 7.4637,
+      "step": 11000
+    },
+    {
+      "epoch": 1.1634965600971268,
+      "grad_norm": 3.0285532474517822,
+      "learning_rate": 3.0608390665047894e-05,
+      "loss": 7.4524,
+      "step": 11500
+    },
+    {
+      "epoch": 1.2140833670578712,
+      "grad_norm": 3.087231159210205,
+      "learning_rate": 2.976527721570215e-05,
+      "loss": 7.4797,
+      "step": 12000
+    },
+    {
+      "epoch": 1.264670174018616,
+      "grad_norm": 2.7964272499084473,
+      "learning_rate": 2.8922163766356404e-05,
+      "loss": 7.4641,
+      "step": 12500
+    },
+    {
+      "epoch": 1.3152569809793606,
+      "grad_norm": 3.68481183052063,
+      "learning_rate": 2.807905031701066e-05,
+      "loss": 7.452,
+      "step": 13000
+    },
+    {
+      "epoch": 1.3658437879401053,
+      "grad_norm": 3.3050220012664795,
+      "learning_rate": 2.7235936867664915e-05,
+      "loss": 7.4593,
+      "step": 13500
+    },
+    {
+      "epoch": 1.41643059490085,
+      "grad_norm": 2.939967155456543,
+      "learning_rate": 2.639282341831917e-05,
+      "loss": 7.4565,
+      "step": 14000
+    },
+    {
+      "epoch": 1.4670174018615945,
+      "grad_norm": 2.9299378395080566,
+      "learning_rate": 2.5549709968973428e-05,
+      "loss": 7.4769,
+      "step": 14500
+    },
+    {
+      "epoch": 1.5176042088223392,
+      "grad_norm": 4.469327449798584,
+      "learning_rate": 2.470659651962768e-05,
+      "loss": 7.4498,
+      "step": 15000
+    },
+    {
+      "epoch": 1.5681910157830838,
+      "grad_norm": 3.3183658123016357,
+      "learning_rate": 2.386348307028194e-05,
+      "loss": 7.4527,
+      "step": 15500
+    },
+    {
+      "epoch": 1.6187778227438283,
+      "grad_norm": 3.6595232486724854,
+      "learning_rate": 2.3020369620936194e-05,
+      "loss": 7.4346,
+      "step": 16000
+    },
+    {
+      "epoch": 1.669364629704573,
+      "grad_norm": 3.1423637866973877,
+      "learning_rate": 2.217725617159045e-05,
+      "loss": 7.4697,
+      "step": 16500
+    },
+    {
+      "epoch": 1.7199514366653177,
+      "grad_norm": 2.9798882007598877,
+      "learning_rate": 2.1334142722244707e-05,
+      "loss": 7.4587,
+      "step": 17000
+    },
+    {
+      "epoch": 1.7705382436260622,
+      "grad_norm": 3.496962547302246,
+      "learning_rate": 2.0491029272898962e-05,
+      "loss": 7.4842,
+      "step": 17500
+    },
+    {
+      "epoch": 1.821125050586807,
+      "grad_norm": 3.2860915660858154,
+      "learning_rate": 1.9647915823553217e-05,
+      "loss": 7.4505,
+      "step": 18000
+    },
+    {
+      "epoch": 1.8717118575475515,
+      "grad_norm": 3.7444324493408203,
+      "learning_rate": 1.8804802374207476e-05,
+      "loss": 7.467,
+      "step": 18500
+    },
+    {
+      "epoch": 1.9222986645082962,
+      "grad_norm": 12.527898788452148,
+      "learning_rate": 1.796168892486173e-05,
+      "loss": 7.4629,
+      "step": 19000
+    },
+    {
+      "epoch": 1.972885471469041,
+      "grad_norm": 3.0026357173919678,
+      "learning_rate": 1.7118575475515986e-05,
+      "loss": 7.4508,
+      "step": 19500
+    },
+    {
+      "epoch": 2.0234722784297854,
+      "grad_norm": 3.080428123474121,
+      "learning_rate": 1.6275462026170245e-05,
+      "loss": 7.4562,
+      "step": 20000
+    },
+    {
+      "epoch": 2.0740590853905303,
+      "grad_norm": 3.0115535259246826,
+      "learning_rate": 1.54323485768245e-05,
+      "loss": 7.4614,
+      "step": 20500
+    },
+    {
+      "epoch": 2.1246458923512748,
+      "grad_norm": 3.0066559314727783,
+      "learning_rate": 1.4589235127478753e-05,
+      "loss": 7.4522,
+      "step": 21000
+    },
+    {
+      "epoch": 2.1752326993120192,
+      "grad_norm": 3.1596481800079346,
+      "learning_rate": 1.3746121678133012e-05,
+      "loss": 7.4373,
+      "step": 21500
+    },
+    {
+      "epoch": 2.225819506272764,
+      "grad_norm": 3.6992828845977783,
+      "learning_rate": 1.2903008228787267e-05,
+      "loss": 7.4649,
+      "step": 22000
+    },
+    {
+      "epoch": 2.2764063132335086,
+      "grad_norm": 2.809210777282715,
+      "learning_rate": 1.2059894779441522e-05,
+      "loss": 7.4695,
+      "step": 22500
+    },
+    {
+      "epoch": 2.3269931201942535,
+      "grad_norm": 3.017029047012329,
+      "learning_rate": 1.1216781330095779e-05,
+      "loss": 7.439,
+      "step": 23000
+    },
+    {
+      "epoch": 2.377579927154998,
+      "grad_norm": 3.747455596923828,
+      "learning_rate": 1.0373667880750036e-05,
+      "loss": 7.4468,
+      "step": 23500
+    },
+    {
+      "epoch": 2.4281667341157425,
+      "grad_norm": 2.9909703731536865,
+      "learning_rate": 9.53055443140429e-06,
+      "loss": 7.4568,
+      "step": 24000
+    },
+    {
+      "epoch": 2.4787535410764874,
+      "grad_norm": 2.6719205379486084,
+      "learning_rate": 8.687440982058546e-06,
+      "loss": 7.4599,
+      "step": 24500
+    },
+    {
+      "epoch": 2.529340348037232,
+      "grad_norm": 3.0623087882995605,
+      "learning_rate": 7.844327532712801e-06,
+      "loss": 7.4613,
+      "step": 25000
+    },
+    {
+      "epoch": 2.5799271549979768,
+      "grad_norm": 3.4007935523986816,
+      "learning_rate": 7.001214083367058e-06,
+      "loss": 7.4496,
+      "step": 25500
+    },
+    {
+      "epoch": 2.6305139619587212,
+      "grad_norm": 3.7014873027801514,
+      "learning_rate": 6.158100634021314e-06,
+      "loss": 7.4569,
+      "step": 26000
+    },
+    {
+      "epoch": 2.6811007689194657,
+      "grad_norm": 2.988811492919922,
+      "learning_rate": 5.314987184675571e-06,
+      "loss": 7.4381,
+      "step": 26500
+    },
+    {
+      "epoch": 2.7316875758802106,
+      "grad_norm": 4.864758014678955,
+      "learning_rate": 4.471873735329827e-06,
+      "loss": 7.4846,
+      "step": 27000
+    },
+    {
+      "epoch": 2.782274382840955,
+      "grad_norm": 2.810575246810913,
+      "learning_rate": 3.628760285984082e-06,
+      "loss": 7.4511,
+      "step": 27500
+    },
+    {
+      "epoch": 2.8328611898017,
+      "grad_norm": 3.2787814140319824,
+      "learning_rate": 2.785646836638338e-06,
+      "loss": 7.4568,
+      "step": 28000
+    },
+    {
+      "epoch": 2.8834479967624445,
+      "grad_norm": 3.12109637260437,
+      "learning_rate": 1.942533387292594e-06,
+      "loss": 7.4372,
+      "step": 28500
+    },
+    {
+      "epoch": 2.934034803723189,
+      "grad_norm": 3.1420302391052246,
+      "learning_rate": 1.0994199379468503e-06,
+      "loss": 7.4484,
+      "step": 29000
+    },
+    {
+      "epoch": 2.9846216106839334,
+      "grad_norm": 3.052818775177002,
+      "learning_rate": 2.5630648860110616e-07,
+      "loss": 7.461,
+      "step": 29500
+    },
+    {
+      "epoch": 3.0,
+      "step": 29652,
+      "total_flos": 1.2851147000984371e+17,
+      "train_loss": 7.479052871051595,
+      "train_runtime": 34661.0306,
+      "train_samples_per_second": 1.711,
+      "train_steps_per_second": 0.855
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 29652,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2851147000984371e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}