Training in progress, epoch 4

checkpoint-675/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49af5e9c7dd614e4d00116982b296ee257dbf971f1a57bbcb84500a99f1807a9
+oid sha256:454be46b2719387ce2b26678b79e53dbff9a3e81379a63918f8323c002e7eca9
 size 1115518581

checkpoint-675/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35c0b7edb05ead061300844844fa916cbd0b57a265d1a380edf9acac95207dca
+oid sha256:ba8fc5a899186a227b2fd27ec6cde7be408b76915ed56d3098cabf35c97b8f72
 size 557982265

checkpoint-675/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04e9983afbab69b9507144eb907b7e9dfda252407067d2de1aca1d814dc47366
+oid sha256:454222c7a01bd085b2f30e74ebbe6fab93821b134d0449f0774c2540f9bda3ae
 size 623

checkpoint-675/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.1801992505788803,
-  "best_model_checkpoint": "outputs/bart-base-detox/checkpoint-405",
+  "best_metric": 0.19366399943828583,
+  "best_model_checkpoint": "outputs/bart-base-detox/checkpoint-675",
   "epoch": 4.9953917050691246,
   "global_step": 675,
   "is_hyper_param_search": false,
@@ -9,72 +9,72 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "learning_rate": 9e-05,
-      "loss": 0.3171,
+      "learning_rate": 9e-06,
+      "loss": 0.5633,
       "step": 135
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.20179320871829987,
-      "eval_runtime": 11.3072,
-      "eval_samples_per_second": 274.16,
-      "eval_steps_per_second": 34.314,
+      "eval_loss": 0.25235414505004883,
+      "eval_runtime": 12.2006,
+      "eval_samples_per_second": 254.085,
+      "eval_steps_per_second": 31.802,
       "step": 135
     },
     {
       "epoch": 2.0,
-      "learning_rate": 8e-05,
-      "loss": 0.1852,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.2589,
       "step": 270
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.18728719651699066,
-      "eval_runtime": 11.1563,
-      "eval_samples_per_second": 277.869,
-      "eval_steps_per_second": 34.778,
+      "eval_loss": 0.21927106380462646,
+      "eval_runtime": 11.2792,
+      "eval_samples_per_second": 274.842,
+      "eval_steps_per_second": 34.4,
       "step": 270
     },
     {
       "epoch": 3.0,
-      "learning_rate": 7e-05,
-      "loss": 0.1559,
+      "learning_rate": 7e-06,
+      "loss": 0.2307,
       "step": 405
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.1801992505788803,
-      "eval_runtime": 11.3199,
-      "eval_samples_per_second": 273.853,
-      "eval_steps_per_second": 34.276,
+      "eval_loss": 0.19929151237010956,
+      "eval_runtime": 11.2313,
+      "eval_samples_per_second": 276.016,
+      "eval_steps_per_second": 34.546,
       "step": 405
     },
     {
       "epoch": 4.0,
-      "learning_rate": 6e-05,
-      "loss": 0.1356,
+      "learning_rate": 6e-06,
+      "loss": 0.2171,
       "step": 540
     },
     {
       "epoch": 4.0,
-      "eval_loss": 0.18711909651756287,
-      "eval_runtime": 11.3935,
-      "eval_samples_per_second": 272.085,
-      "eval_steps_per_second": 34.054,
+      "eval_loss": 0.20016591250896454,
+      "eval_runtime": 11.0923,
+      "eval_samples_per_second": 279.473,
+      "eval_steps_per_second": 34.979,
       "step": 540
     },
     {
       "epoch": 5.0,
-      "learning_rate": 5e-05,
-      "loss": 0.1151,
+      "learning_rate": 5e-06,
+      "loss": 0.2027,
       "step": 675
     },
     {
       "epoch": 5.0,
-      "eval_loss": 0.19263018667697906,
-      "eval_runtime": 11.4175,
-      "eval_samples_per_second": 271.514,
-      "eval_steps_per_second": 33.983,
+      "eval_loss": 0.19366399943828583,
+      "eval_runtime": 11.2232,
+      "eval_samples_per_second": 276.213,
+      "eval_steps_per_second": 34.571,
       "step": 675
     }
   ],

checkpoint-675/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6779c0d7bfc5cc8b7f502411db449902ffdb3fd6d5cc4758f90defaa037cdfa
+oid sha256:cd8019ba81e4d8cd7e878f72b37c14bf5f28f7f6b5acd2cf343bb5ba08c77b6a
 size 3183

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d1c0097f49c1da6253017544d8b7e2be9ad69411aef2cea8d2f938d4d27d075
+oid sha256:ba8fc5a899186a227b2fd27ec6cde7be408b76915ed56d3098cabf35c97b8f72
 size 557982265