Training in progress, epoch 0

all_results.json

@@ -5,11 +5,11 @@
     "eval_loss": 0.4917445778846741,
     "eval_precision": 0.9019841269841271,
     "eval_recall": 0.888888888888889,
-    "eval_runtime": 2.8796,
-    "eval_samples_per_second": 17.363,
-    "eval_steps_per_second": 1.389,
-    "train_loss": 0.8048010190327962,
-    "train_runtime": 101.246,
-    "train_samples_per_second": 19.606,
+    "eval_runtime": 2.7009,
+    "eval_samples_per_second": 18.512,
+    "eval_steps_per_second": 1.481,
+    "train_loss": 0.8048010031382243,
+    "train_runtime": 101.5046,
+    "train_samples_per_second": 19.556,
     "train_steps_per_second": 0.296
 }

eval_results.json

@@ -4,7 +4,7 @@
     "eval_loss": 0.4917445778846741,
     "eval_precision": 0.9019841269841271,
     "eval_recall": 0.888888888888889,
-    "eval_runtime": 2.8796,
-    "eval_samples_per_second": 17.363,
-    "eval_steps_per_second": 1.389
+    "eval_runtime": 2.7009,
+    "eval_samples_per_second": 18.512,
+    "eval_steps_per_second": 1.481
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1a39cfc8adad56bf2ee22ca8629aa0029137a9500168ee7d233da5e00e31526
+oid sha256:45472aab20ab139959ef06b6fd6e930443066f347b6c459a418f7ecb7be4843a
 size 111550573

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 4.8,
-    "train_loss": 0.8048010190327962,
-    "train_runtime": 101.246,
-    "train_samples_per_second": 19.606,
+    "train_loss": 0.8048010031382243,
+    "train_runtime": 101.5046,
+    "train_samples_per_second": 19.556,
     "train_steps_per_second": 0.296
 }

trainer_state.json

@@ -15,9 +15,9 @@
       "eval_loss": 1.1803159713745117,
       "eval_precision": 0.6789160839160839,
       "eval_recall": 0.6868831168831169,
-      "eval_runtime": 3.3618,
-      "eval_samples_per_second": 14.873,
-      "eval_steps_per_second": 1.19,
+      "eval_runtime": 3.4169,
+      "eval_samples_per_second": 14.633,
+      "eval_steps_per_second": 1.171,
       "step": 6
     },
     {
@@ -30,24 +30,24 @@
       "epoch": 1.92,
       "eval_accuracy": 0.84,
       "eval_f1": 0.8387969924812031,
-      "eval_loss": 0.7862006425857544,
+      "eval_loss": 0.7862005829811096,
       "eval_precision": 0.8603030303030303,
       "eval_recall": 0.856969696969697,
-      "eval_runtime": 2.7831,
-      "eval_samples_per_second": 17.966,
-      "eval_steps_per_second": 1.437,
+      "eval_runtime": 2.6641,
+      "eval_samples_per_second": 18.768,
+      "eval_steps_per_second": 1.501,
       "step": 12
     },
     {
       "epoch": 2.88,
       "eval_accuracy": 0.9,
       "eval_f1": 0.9023978919631095,
-      "eval_loss": 0.5749024748802185,
+      "eval_loss": 0.5749024152755737,
       "eval_precision": 0.9034848484848486,
       "eval_recall": 0.9103030303030304,
-      "eval_runtime": 2.6475,
-      "eval_samples_per_second": 18.886,
-      "eval_steps_per_second": 1.511,
+      "eval_runtime": 2.6511,
+      "eval_samples_per_second": 18.86,
+      "eval_steps_per_second": 1.509,
       "step": 18
     },
     {
@@ -60,12 +60,12 @@
       "epoch": 4.0,
       "eval_accuracy": 0.9,
       "eval_f1": 0.9023978919631095,
-      "eval_loss": 0.47980964183807373,
+      "eval_loss": 0.47980961203575134,
       "eval_precision": 0.9034848484848486,
       "eval_recall": 0.9103030303030304,
-      "eval_runtime": 2.685,
-      "eval_samples_per_second": 18.622,
-      "eval_steps_per_second": 1.49,
+      "eval_runtime": 2.6994,
+      "eval_samples_per_second": 18.523,
+      "eval_steps_per_second": 1.482,
       "step": 25
     },
     {
@@ -78,21 +78,21 @@
       "epoch": 4.8,
       "eval_accuracy": 0.9,
       "eval_f1": 0.9023978919631095,
-      "eval_loss": 0.46124908328056335,
+      "eval_loss": 0.4612491726875305,
       "eval_precision": 0.9034848484848486,
       "eval_recall": 0.9103030303030304,
-      "eval_runtime": 2.7597,
-      "eval_samples_per_second": 18.118,
-      "eval_steps_per_second": 1.449,
+      "eval_runtime": 2.6906,
+      "eval_samples_per_second": 18.583,
+      "eval_steps_per_second": 1.487,
       "step": 30
     },
     {
       "epoch": 4.8,
       "step": 30,
       "total_flos": 1.4114178534172262e+17,
-      "train_loss": 0.8048010190327962,
-      "train_runtime": 101.246,
-      "train_samples_per_second": 19.606,
+      "train_loss": 0.8048010031382243,
+      "train_runtime": 101.5046,
+      "train_samples_per_second": 19.556,
       "train_steps_per_second": 0.296
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab3212533198c3de7e5dda4341f6ae79dafe0f3ee0a05e1d3c333c0f4df3a6a
+oid sha256:4c51a483b7010c9031af33c45a848c04fac70447e17aacfc4ec922618a70f1b6
 size 4155