End of training

all_results.json

@@ -1,25 +1,25 @@
 {
-    "epoch": 4.0,
-    "eval_accuracy": 0.9857096459889575,
+    "epoch": 6.0,
+    "eval_accuracy": 0.9899317960376746,
     "eval_f1": 0.0,
-    "eval_loss": 0.04534918814897537,
+    "eval_loss": 0.026788420975208282,
     "eval_precision": 0.0,
     "eval_recall": 0.0,
-    "eval_runtime": 2.1196,
+    "eval_runtime": 1.9243,
     "eval_samples": 124,
-    "eval_samples_per_second": 58.502,
-    "eval_steps_per_second": 1.887,
-    "predict_accuracy": 0.9871606749816582,
+    "eval_samples_per_second": 64.438,
+    "eval_steps_per_second": 2.079,
+    "predict_accuracy": 0.9900953778429934,
     "predict_f1": 0.0,
-    "predict_loss": 0.0440601110458374,
+    "predict_loss": 0.027090908959507942,
     "predict_precision": 0.0,
     "predict_recall": 0.0,
-    "predict_runtime": 1.84,
-    "predict_samples_per_second": 55.979,
-    "predict_steps_per_second": 2.174,
-    "train_loss": 0.19345927238464355,
-    "train_runtime": 231.2313,
-    "train_samples": 950,
-    "train_samples_per_second": 16.434,
-    "train_steps_per_second": 0.069
+    "predict_runtime": 1.9685,
+    "predict_samples_per_second": 52.325,
+    "predict_steps_per_second": 2.032,
+    "train_loss": 0.13241314888000488,
+    "train_runtime": 520.3829,
+    "train_samples": 957,
+    "train_samples_per_second": 11.034,
+    "train_steps_per_second": 0.046
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 4.0,
-    "eval_accuracy": 0.9857096459889575,
+    "epoch": 6.0,
+    "eval_accuracy": 0.9899317960376746,
     "eval_f1": 0.0,
-    "eval_loss": 0.04534918814897537,
+    "eval_loss": 0.026788420975208282,
     "eval_precision": 0.0,
     "eval_recall": 0.0,
-    "eval_runtime": 2.1196,
+    "eval_runtime": 1.9243,
     "eval_samples": 124,
-    "eval_samples_per_second": 58.502,
-    "eval_steps_per_second": 1.887
+    "eval_samples_per_second": 64.438,
+    "eval_steps_per_second": 2.079
 }

predict_results.json

@@ -1,10 +1,10 @@
 {
-    "predict_accuracy": 0.9871606749816582,
+    "predict_accuracy": 0.9900953778429934,
     "predict_f1": 0.0,
-    "predict_loss": 0.0440601110458374,
+    "predict_loss": 0.027090908959507942,
     "predict_precision": 0.0,
     "predict_recall": 0.0,
-    "predict_runtime": 1.84,
-    "predict_samples_per_second": 55.979,
-    "predict_steps_per_second": 2.174
+    "predict_runtime": 1.9685,
+    "predict_samples_per_second": 52.325,
+    "predict_steps_per_second": 2.032
 }

predictions.txt

@@ -7,13 +7,13 @@ N N N N N N N N N Y N Y N N N N N N N N
 N N N N N N N N N Y N N N N
 N N N N N N N N N N N N N N N N N N N N N Y N N N
 N N N N N N N N N N N N Y N N N N
-N N N N N N Y N N Y N N N N N N N N N N N Y N
+N N N N N N N N N Y N N N N N N N N N N N Y N
 N N N N Y N N N Y N N N N N N N N N N N N N N N N N N N N N N Y N N N N
 N N N N N N N N N N N N N Y N N N N N N
 N Y N N N N N N N N N N N N N N N N
 N N N N N N N N N N N N N N N N N N N N N N N N N N N N Y N
 N N N N N N N N N N N Y N N N N N N N N N N N N N N N
-N N N N N N N N Y Y N
+N N N N N N N N N Y N
 N N N N N N N N N N N N Y N N N N N
 N N N Y N N N N N N N N N N N N N N N N N N N N Y N N
 N N N N N N N N N Y N N N N N N N N N Y N N N
@@ -25,21 +25,21 @@ N N N N N N N N N N Y N N N N N N N N N N N N
 N N N N N N N N N N N Y N N N N N N N N N N
 N N N N N N N N N N N N N N N N N N Y N N N N N
 N N N N N N Y N N N
-N N N N N N N N N N N N N N N N N N N N N N N Y N N N N N N N N N N N N Y N N N N N N N N N
+N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N Y N N N N N N N N N
 N N N N N N N N Y N N N N N N N N N N N
 N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N Y N N N N
 N N N N N N N N N N N N N N N N N N N N Y N N N N N N N N N N N Y N N N N N N N N Y N N N N
 N N N N N N N N N N N N Y N N N N N
 N N N N N N N N N N N N N N N N N Y N N N N N
-N N N N N Y N N N N N N N N N N N N N N N N N N
-N Y N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N
+N N N N N N N Y N N N N N N N N N N N N N N N N
+N Y N N N N N N N N N N Y N N N N N N N N N N N N N N N N N N N N
 N N N N N N N N N N N N Y N
 N N N N N N N N N N N N N N N N N N N N N
 N N N N N N N N N N N N N N N N Y N N N N N N N N N N N N N N N N N N N N N N N
 N N Y N N N N N N N N N N N N N N N N N N N N N N N
 N N N N N N N Y N N N N N N N
 N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N Y N N N N
-N Y N N N N N N N N N Y N N N N N N N N N N N N N N N N N N N N N N N
+N N N N N N N N N N N Y N N N N N N N N N N N N N N N N N N N N N N N
 N N N N N N N N Y N N N N N
 N N N Y N N N N N N N N N N N N N N
 N N N N N N N N N N N N N N N N N N N N Y N N N N N N N N N Y N N N N N
@@ -47,21 +47,21 @@ N N N N N N N N N N N Y N N N N N
 N N N N Y N
 N N N N N N N N N N N Y N N N N N N N N Y N N N N N N N N N
 N N Y N N N N N N N N N N N N N N N N N N N N N N N N N N N
-N N N N N N N N N N N N N N N N N N N N Y N N N N N N
+N N N N N N N N N N N N N N N N N N N N N N N N N N N
 N N N N N N N Y N N N N N N N N N Y N N N N N N N N N
 N N N N N N N N N Y N N N N N
 N N N N N N N N N N Y N N N N
 N N N N N N Y N N N N N N N N N N N N N N N N
 N N N N N N N N Y N N N N N N N N N N N N N N N N N N N N N N N
 N N N N N N Y N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N
-N N N Y N N N N N N N N N N Y N N N N N N N N N
+N N N Y N N N N N N N N N N N N N N N N N N N N
 N N N N N N N N N Y N
 N N N N N N Y N N N N N N N N N N Y N N N N N N N N N N N N
 N N N N N N N N N N N N N N N N N N N Y N N N N N N N N
 N N N N N N N N N N N N N N N N N N N N N N N N
-N N N N N N N N N N N N N N N N N N N Y N N N N N N N N Y N N N N N N N N N N N N N N N N N
+N N N N N N N N N N N N N N N N N N N Y N N N N N N N N Y N N N N N N N N Y N N N N N N N N
 N N N N N N N N N N N N N N N N N N N N N N Y N
-N N N N N N N N N N N N N N N N N N
+N N N N N N N N N N N N N N N Y N N
 N N N N N N N N N N N N N Y N
 N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N Y N N N N N N N N N N
 N N N N N Y N N N N N N
@@ -77,27 +77,27 @@ N N N N N N N N N N N N N N N N N N N N N N Y N N N N N N N N N N N N N N N N N
 N N N N N N N N N N N N N N N N N N
 N N N Y N N N N N N
 N N N N N N N N N N N N N N N N N N N N N N N Y N N N N N N N N N N N N
-N N N N N N N Y N N N N N Y N N N N N N N N N N N N N N N N N N N N N N N
+N N N N N N N N N N N N N Y N N N N N N N N N N N N N N N N N N N N N N N
 N N N N N N N N N N N N N Y N N N N N N N N N N N N
 N N N N N N Y N N N N N N N N
 N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N Y N N N N N N N N N
 N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N Y N N
-N N N N N N N N N N N N N Y N N N N N N N N N N N Y N N N N N N N N N
+N N N N N N N N N N N N N Y N N N N N N N N N N N N N N N N N N N N N
 N N N N N N N N N N N N N N N N N N N Y N N N N N N N N N N N N
 N N Y N N N N N N N
 N N N N N N N N N N N Y N
 N N N N N N N N N N N N N N N N N N N N N N N Y N N
-N N N N Y N N N N N N N N N N N N N
+N N N N N N N N N N N N N N N N N N
 N N N Y N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N
 N N N N N N N N N Y N N N N N N N N
-N N N N N N N N N N N N N N N N N N N N N N N N N N N N N
+N N N N N N N N N N Y N N N N N N N N N N N N N N N N N N
 N N N N Y N N N N N N N N N N N N
 N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N Y N N N N N N N N N N N N N N N N N N N N N N N N N N N N
 N N N N N N Y N N N N N N N N N N N
 N N N N N N N N N N N N N N N N N N N N N N N N N N N Y N N N N N N N
 N N N N Y N N N N N N N N N N N N N N N N N N N N N N N N N N N
 N N Y N N N N N N N N N N N N N N N N
-N N N Y N N N N
+N N N Y N Y N N
 N N N Y N N N N N N N N N N N N N N N N N
 N N Y N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N N
 N N N N N N N N N N N N N N N N N N N N N Y N N N

runs/Nov16_01-46-07_dell-NF5468M6/events.out.tfevents.1668535186.dell-NF5468M6.6991.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a00e5f48182daf252c992b88e417d6da5fdc64d6850567a4ee62c79f1aa8283
+size 503

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 4.0,
-    "train_loss": 0.19345927238464355,
-    "train_runtime": 231.2313,
-    "train_samples": 950,
-    "train_samples_per_second": 16.434,
-    "train_steps_per_second": 0.069
+    "epoch": 6.0,
+    "train_loss": 0.13241314888000488,
+    "train_runtime": 520.3829,
+    "train_samples": 957,
+    "train_samples_per_second": 11.034,
+    "train_steps_per_second": 0.046
 }

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.04534918814897537,
-  "best_model_checkpoint": "./roberta-large-condaqa-neg-tag-token-classifier/checkpoint-16",
-  "epoch": 4.0,
-  "global_step": 16,
+  "best_metric": 0.026788420975208282,
+  "best_model_checkpoint": "./roberta-large-condaqa-neg-tag-token-classifier/checkpoint-24",
+  "epoch": 6.0,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,11 +11,11 @@
       "epoch": 1.0,
       "eval_accuracy": 0.9587528418317636,
       "eval_f1": 0.0,
-      "eval_loss": 0.1548939347267151,
+      "eval_loss": 0.15255515277385712,
       "eval_precision": 0.0,
       "eval_recall": 0.0,
-      "eval_runtime": 1.8568,
-      "eval_samples_per_second": 66.78,
+      "eval_runtime": 1.8569,
+      "eval_samples_per_second": 66.777,
       "eval_steps_per_second": 2.154,
       "step": 4
     },
@@ -23,51 +23,75 @@
       "epoch": 2.0,
       "eval_accuracy": 0.9587528418317636,
       "eval_f1": 0.0,
-      "eval_loss": 0.1006716936826706,
+      "eval_loss": 0.0874876081943512,
       "eval_precision": 0.0,
       "eval_recall": 0.0,
-      "eval_runtime": 2.0399,
-      "eval_samples_per_second": 60.786,
-      "eval_steps_per_second": 1.961,
+      "eval_runtime": 2.0477,
+      "eval_samples_per_second": 60.555,
+      "eval_steps_per_second": 1.953,
       "step": 8
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.9818122767132186,
+      "eval_accuracy": 0.9876583306268268,
       "eval_f1": 0.0,
-      "eval_loss": 0.0592331625521183,
+      "eval_loss": 0.03961525484919548,
       "eval_precision": 0.0,
       "eval_recall": 0.0,
-      "eval_runtime": 2.0042,
-      "eval_samples_per_second": 61.87,
-      "eval_steps_per_second": 1.996,
+      "eval_runtime": 2.0055,
+      "eval_samples_per_second": 61.83,
+      "eval_steps_per_second": 1.995,
       "step": 12
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.9857096459889575,
+      "eval_accuracy": 0.9899317960376746,
       "eval_f1": 0.0,
-      "eval_loss": 0.04534918814897537,
+      "eval_loss": 0.03219746798276901,
       "eval_precision": 0.0,
       "eval_recall": 0.0,
-      "eval_runtime": 1.8522,
-      "eval_samples_per_second": 66.948,
-      "eval_steps_per_second": 2.16,
+      "eval_runtime": 1.8577,
+      "eval_samples_per_second": 66.749,
+      "eval_steps_per_second": 2.153,
       "step": 16
     },
     {
-      "epoch": 4.0,
-      "step": 16,
-      "total_flos": 598453706860920.0,
-      "train_loss": 0.19345927238464355,
-      "train_runtime": 231.2313,
-      "train_samples_per_second": 16.434,
-      "train_steps_per_second": 0.069
+      "epoch": 5.0,
+      "eval_accuracy": 0.9905813575836311,
+      "eval_f1": 0.0,
+      "eval_loss": 0.026981903240084648,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 1.8937,
+      "eval_samples_per_second": 65.479,
+      "eval_steps_per_second": 2.112,
+      "step": 20
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9899317960376746,
+      "eval_f1": 0.0,
+      "eval_loss": 0.026788420975208282,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 1.8835,
+      "eval_samples_per_second": 65.835,
+      "eval_steps_per_second": 2.124,
+      "step": 24
+    },
+    {
+      "epoch": 6.0,
+      "step": 24,
+      "total_flos": 897265181578104.0,
+      "train_loss": 0.13241314888000488,
+      "train_runtime": 520.3829,
+      "train_samples_per_second": 11.034,
+      "train_steps_per_second": 0.046
     }
   ],
-  "max_steps": 16,
-  "num_train_epochs": 4,
-  "total_flos": 598453706860920.0,
+  "max_steps": 24,
+  "num_train_epochs": 6,
+  "total_flos": 897265181578104.0,
   "trial_name": null,
   "trial_params": null
 }