Training in progress, epoch 2

checkpoint-405/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e77c8a2a5fad17d46427af1d8a570e4d5fd98c6b9ed138860d70a3bfe45c497a
+oid sha256:1d06c66d25a583e1552589360dd807828fa2e9ef8fe064adf663c2930cd10750
 size 1115518581

checkpoint-405/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b214a195ba865a570b4c0ca7858a07d3cdf972c6a40b69118e204806f82334d3
+oid sha256:61ada5f16a59af821e82557d0cc1154b9a8317ada4b526eedac4e607d1c6f078
 size 557982265

checkpoint-405/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:361b412c6099209dd7c32c3cf59809aa5d7b27574edb1597b9b27827ea576a15
+oid sha256:89be3ff2dd97ecabb1e4c4328f68780edb24a6834a6485d041b06fde96f5ac91
 size 623

checkpoint-405/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.1801992505788803,
+  "best_metric": 0.19929151237010956,
   "best_model_checkpoint": "outputs/bart-base-detox/checkpoint-405",
   "epoch": 2.9953917050691246,
   "global_step": 405,
@@ -9,44 +9,44 @@
   "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
     }
   ],

checkpoint-405/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 sha256:1328007474fa4e55660b5739283edac44d62b1a9128017d3afdee46e71e1d830
+oid sha256:61ada5f16a59af821e82557d0cc1154b9a8317ada4b526eedac4e607d1c6f078
 size 557982265