Training in progress, epoch 4, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e97d1601b2e3f59fcff76a066bd87f8bca7ca2f80a0c253e165a2cde4b1766e
+oid sha256:abcf9278bf80f871bbda4ffa9be883d3b9d1c52089b9d33c2ca021af12bc00f8
 size 615849402

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c7464e96410b0803829fcaf50c827a2df990e4d630ae154ac0f3d16961ae70f
+oid sha256:6da080e8fde1ff422407acfc1b0714d8f6aa1266c97fc465e5d731386708176d
 size 307910594

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7dac90b8b7aae7204dbe1f1064bf8fa4437e2d9a0b4c17eaf969810bf8a5a83
+oid sha256:15552249b9c446195b97b2b0abd07e68ddc68dd1792bd9d1e769855d57c06f5e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee3a1f39b0649bc03eb60d23712514a784906b72a24cf2557a6e6d26f75c9b70
+oid sha256:8387f825847a9b8a2c8387203584ce1062acc3caff7113d13f9f01240448459b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.009255478158593178,
-  "best_model_checkpoint": "flan-search-terms/checkpoint-4500",
-  "epoch": 3.0,
+  "best_metric": 0.007984320633113384,
+  "best_model_checkpoint": "flan-search-terms/checkpoint-6000",
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 4500,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -100,13 +100,44 @@
       "eval_samples_per_second": 11.896,
       "eval_steps_per_second": 1.487,
       "step": 4500
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.0127,
+      "step": 5000
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.0119,
+      "step": 5500
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0114,
+      "step": 6000
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 8.544666666666666,
+      "eval_loss": 0.007984320633113384,
+      "eval_rouge1": 5.3013,
+      "eval_rouge2": 4.448,
+      "eval_rougeL": 4.9117,
+      "eval_rougeLsum": 4.9183,
+      "eval_runtime": 255.3664,
+      "eval_samples_per_second": 11.748,
+      "eval_steps_per_second": 1.468,
+      "step": 6000
     }
   ],
   "logging_steps": 500,
   "max_steps": 7500,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 6692058169344000.0,
+  "total_flos": 8922744225792000.0,
   "trial_name": null,
   "trial_params": null
 }