Reset model

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Rouge1
       type: rouge
-      value: 89.6649
+      value: 14.9574
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,12 +31,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the searde/dataset-financial-documents-3 3.0.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0967
-- Rouge1: 89.6649
-- Rouge2: 68.3919
-- Rougel: 89.4415
-- Rougelsum: 89.5589
-- Gen Len: 39.3769
+- Loss: 3.0505
+- Rouge1: 14.9574
+- Rouge2: 0.0
+- Rougel: 8.4517
+- Rougelsum: 12.4858
+- Gen Len: 63.0
 
 ## Model description
 

all_results.json

@@ -1,18 +1,18 @@
 {
     "epoch": 3.0,
-    "eval_gen_len": 39.37688442211055,
-    "eval_loss": 0.09672751277685165,
-    "eval_rouge1": 89.6649,
-    "eval_rouge2": 68.3919,
-    "eval_rougeL": 89.4415,
-    "eval_rougeLsum": 89.5589,
-    "eval_runtime": 169.8618,
-    "eval_samples": 199,
-    "eval_samples_per_second": 1.172,
-    "eval_steps_per_second": 0.294,
-    "train_loss": 0.19669942220052083,
-    "train_runtime": 181.9658,
-    "train_samples": 199,
-    "train_samples_per_second": 3.281,
-    "train_steps_per_second": 0.824
+    "eval_gen_len": 63.0,
+    "eval_loss": 3.0504558086395264,
+    "eval_rouge1": 14.9574,
+    "eval_rouge2": 0.0,
+    "eval_rougeL": 8.4517,
+    "eval_rougeLsum": 12.4858,
+    "eval_runtime": 13.4834,
+    "eval_samples": 2,
+    "eval_samples_per_second": 0.148,
+    "eval_steps_per_second": 0.074,
+    "train_loss": 3.8336060841878257,
+    "train_runtime": 23.7681,
+    "train_samples": 8,
+    "train_samples_per_second": 1.01,
+    "train_steps_per_second": 0.252
 }

eval_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 3.0,
-    "eval_gen_len": 39.37688442211055,
-    "eval_loss": 0.09672751277685165,
-    "eval_rouge1": 89.6649,
-    "eval_rouge2": 68.3919,
-    "eval_rougeL": 89.4415,
-    "eval_rougeLsum": 89.5589,
-    "eval_runtime": 169.8618,
-    "eval_samples": 199,
-    "eval_samples_per_second": 1.172,
-    "eval_steps_per_second": 0.294
+    "eval_gen_len": 63.0,
+    "eval_loss": 3.0504558086395264,
+    "eval_rouge1": 14.9574,
+    "eval_rouge2": 0.0,
+    "eval_rougeL": 8.4517,
+    "eval_rougeLsum": 12.4858,
+    "eval_runtime": 13.4834,
+    "eval_samples": 2,
+    "eval_samples_per_second": 0.148,
+    "eval_steps_per_second": 0.074
 }

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 128,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "train_loss": 0.19669942220052083,
-    "train_runtime": 181.9658,
-    "train_samples": 199,
-    "train_samples_per_second": 3.281,
-    "train_steps_per_second": 0.824
+    "train_loss": 3.8336060841878257,
+    "train_runtime": 23.7681,
+    "train_samples": 8,
+    "train_samples_per_second": 1.01,
+    "train_steps_per_second": 0.252
 }

trainer_state.json

@@ -2,24 +2,24 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 3.0,
-  "global_step": 150,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 3.0,
-      "step": 150,
-      "total_flos": 44938500538368.0,
-      "train_loss": 0.19669942220052083,
-      "train_runtime": 181.9658,
-      "train_samples_per_second": 3.281,
-      "train_steps_per_second": 0.824
+      "step": 6,
+      "total_flos": 6496406470656.0,
+      "train_loss": 3.8336060841878257,
+      "train_runtime": 23.7681,
+      "train_samples_per_second": 1.01,
+      "train_steps_per_second": 0.252
     }
   ],
-  "max_steps": 150,
+  "max_steps": 6,
   "num_train_epochs": 3,
-  "total_flos": 44938500538368.0,
+  "total_flos": 6496406470656.0,
   "trial_name": null,
   "trial_params": null
 }