End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: facebook/bart-base
 tags:
 - generated_from_trainer
+datasets:
+- learn3r/gov_report_memsum_oracle
 model-index:
 - name: bart_memsum
   results: []
@@ -13,7 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bart_memsum
 
-This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
+This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the learn3r/gov_report_memsum_oracle dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0000
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 9.96,
+    "eval_loss": 1.7506826566204836e-07,
+    "eval_runtime": 2.4534,
+    "eval_samples": 972,
+    "eval_samples_per_second": 396.186,
+    "eval_steps_per_second": 12.636,
+    "train_loss": 0.08629453677293734,
+    "train_runtime": 13279.1496,
+    "train_samples": 17457,
+    "train_samples_per_second": 13.146,
+    "train_steps_per_second": 0.013
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.96,
+    "eval_loss": 1.7506826566204836e-07,
+    "eval_runtime": 2.4534,
+    "eval_samples": 972,
+    "eval_samples_per_second": 396.186,
+    "eval_steps_per_second": 12.636
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.96,
+    "train_loss": 0.08629453677293734,
+    "train_runtime": 13279.1496,
+    "train_samples": 17457,
+    "train_samples_per_second": 13.146,
+    "train_steps_per_second": 0.013
+}

trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.963369963369964,
+  "global_step": 170,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00018823529411764707,
+      "loss": 1.4378,
+      "step": 10
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00017647058823529413,
+      "loss": 0.0123,
+      "step": 20
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.0001647058823529412,
+      "loss": 0.0039,
+      "step": 30
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 0.00015294117647058822,
+      "loss": 0.0014,
+      "step": 40
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0001411764705882353,
+      "loss": 0.0011,
+      "step": 50
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 0.00012941176470588237,
+      "loss": 0.0042,
+      "step": 60
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 0.00011764705882352942,
+      "loss": 0.0009,
+      "step": 70
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 0.00010588235294117647,
+      "loss": 0.0011,
+      "step": 80
+    },
+    {
+      "epoch": 5.27,
+      "learning_rate": 9.411764705882353e-05,
+      "loss": 0.0013,
+      "step": 90
+    },
+    {
+      "epoch": 5.86,
+      "learning_rate": 8.23529411764706e-05,
+      "loss": 0.0009,
+      "step": 100
+    },
+    {
+      "epoch": 6.45,
+      "learning_rate": 7.058823529411765e-05,
+      "loss": 0.0003,
+      "step": 110
+    },
+    {
+      "epoch": 7.03,
+      "learning_rate": 5.882352941176471e-05,
+      "loss": 0.0006,
+      "step": 120
+    },
+    {
+      "epoch": 7.62,
+      "learning_rate": 4.705882352941177e-05,
+      "loss": 0.0004,
+      "step": 130
+    },
+    {
+      "epoch": 8.21,
+      "learning_rate": 3.529411764705883e-05,
+      "loss": 0.0005,
+      "step": 140
+    },
+    {
+      "epoch": 8.79,
+      "learning_rate": 2.3529411764705884e-05,
+      "loss": 0.0001,
+      "step": 150
+    },
+    {
+      "epoch": 9.38,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 0.0002,
+      "step": 160
+    },
+    {
+      "epoch": 9.96,
+      "learning_rate": 0.0,
+      "loss": 0.0001,
+      "step": 170
+    },
+    {
+      "epoch": 9.96,
+      "step": 170,
+      "total_flos": 1359589640048640.0,
+      "train_loss": 0.08629453677293734,
+      "train_runtime": 13279.1496,
+      "train_samples_per_second": 13.146,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "max_steps": 170,
+  "num_train_epochs": 10,
+  "total_flos": 1359589640048640.0,
+  "trial_name": null,
+  "trial_params": null
+}