update

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 3.0,
-    "eval_combined_score": 0.8842865440954153,
-    "eval_loss": 0.5158146023750305,
-    "eval_pearson": 0.8864821563911284,
-    "eval_runtime": 10.2158,
+    "epoch": 2.0,
+    "eval_combined_score": 0.8888898431700671,
+    "eval_loss": 0.4864096939563751,
+    "eval_pearson": 0.8905037519574853,
+    "eval_runtime": 10.6914,
     "eval_samples": 1500,
-    "eval_samples_per_second": 146.832,
-    "eval_spearmanr": 0.8820909317997021,
-    "eval_steps_per_second": 18.403,
-    "train_runtime": 312.8324,
+    "eval_samples_per_second": 140.299,
+    "eval_spearmanr": 0.8872759343826491,
+    "eval_steps_per_second": 17.584,
+    "train_runtime": 502.9099,
     "train_samples": 5749,
-    "train_samples_per_second": 55.132,
-    "train_steps_per_second": 1.726
+    "train_samples_per_second": 22.863,
+    "train_steps_per_second": 1.432
 }

eval_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 3.0,
-    "eval_combined_score": 0.8842865440954153,
-    "eval_loss": 0.5158146023750305,
-    "eval_pearson": 0.8864821563911284,
-    "eval_runtime": 10.2158,
+    "epoch": 2.0,
+    "eval_combined_score": 0.8888898431700671,
+    "eval_loss": 0.4864096939563751,
+    "eval_pearson": 0.8905037519574853,
+    "eval_runtime": 10.6914,
     "eval_samples": 1500,
-    "eval_samples_per_second": 146.832,
-    "eval_spearmanr": 0.8820909317997021,
-    "eval_steps_per_second": 18.403
-}
+    "eval_samples_per_second": 140.299,
+    "eval_spearmanr": 0.8872759343826491,
+    "eval_steps_per_second": 17.584
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deb506692f73c32142865d867d7e01895fdb8f1bdbd1e6ee2ee91e9af466bbdf
-size 438019344
+oid sha256:1701819d587ef43ec1314339ea46a6f3611033e50fd7cb64fc6460b9acd1c9d9
+size 438019349

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 3.0,
-    "train_runtime": 312.8324,
+    "epoch": 2.0,
+    "train_runtime": 502.9099,
     "train_samples": 5749,
-    "train_samples_per_second": 55.132,
-    "train_steps_per_second": 1.726
+    "train_samples_per_second": 22.863,
+    "train_steps_per_second": 1.432
 }

trainer_state.json

@@ -1,30 +1,30 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
-  "global_step": 540,
+  "epoch": 2.0,
+  "global_step": 720,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 2.78,
-      "learning_rate": 1.4814814814814815e-06,
-      "loss": 0.7909,
+      "epoch": 1.39,
+      "learning_rate": 9.166666666666668e-06,
+      "loss": 0.8341,
       "step": 500
     },
     {
-      "epoch": 3.0,
-      "step": 540,
-      "total_flos": 1450178654379264.0,
-      "train_runtime": 312.8324,
-      "train_samples_per_second": 55.132,
-      "train_steps_per_second": 1.726
+      "epoch": 2.0,
+      "step": 720,
+      "total_flos": 966785769586176.0,
+      "train_runtime": 502.9099,
+      "train_samples_per_second": 22.863,
+      "train_steps_per_second": 1.432
     }
   ],
-  "max_steps": 540,
-  "num_train_epochs": 3,
-  "total_flos": 1450178654379264.0,
+  "max_steps": 720,
+  "num_train_epochs": 2,
+  "total_flos": 966785769586176.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04d81cc38655a6a9bc4e5af973350be6f009da12a33bcf21903c7caa120864dc
-size 2415
+oid sha256:bcbba026b338cdd88bc77246025340ba6b23d056be236999fa4a7a54541d28dc
+size 2479