Training in progress, epoch 5, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abcf9278bf80f871bbda4ffa9be883d3b9d1c52089b9d33c2ca021af12bc00f8
+oid sha256:6fbe6d608a942537e6292b2872403242323d8c3cd58fcf734be83e3dc6228f31
 size 615849402

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6da080e8fde1ff422407acfc1b0714d8f6aa1266c97fc465e5d731386708176d
+oid sha256:d2ef2d22ca2bff3aa3c27e6b5bb5fa7b38bb5a6fe226aa337d275d9e441e1668
 size 307910594

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15552249b9c446195b97b2b0abd07e68ddc68dd1792bd9d1e769855d57c06f5e
+oid sha256:6806db7e12e994c3a92c927520fdf44bec2f8e45d8dde397c2681914b7c93270
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8387f825847a9b8a2c8387203584ce1062acc3caff7113d13f9f01240448459b
+oid sha256:3e95f78bbbb9b613376b4c17ce129da2369a70a8610283ee10e8332a35cb2fc8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.007984320633113384,
-  "best_model_checkpoint": "flan-search-terms/checkpoint-6000",
-  "epoch": 4.0,
+  "best_metric": 0.0076544685289263725,
+  "best_model_checkpoint": "flan-search-terms/checkpoint-7500",
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 6000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,13 +131,44 @@
       "eval_samples_per_second": 11.748,
       "eval_steps_per_second": 1.468,
       "step": 6000
+    },
+    {
+      "epoch": 4.33,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.011,
+      "step": 6500
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.0112,
+      "step": 7000
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.0105,
+      "step": 7500
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 8.819,
+      "eval_loss": 0.0076544685289263725,
+      "eval_rouge1": 5.2275,
+      "eval_rouge2": 4.3657,
+      "eval_rougeL": 4.8365,
+      "eval_rougeLsum": 4.8414,
+      "eval_runtime": 257.9989,
+      "eval_samples_per_second": 11.628,
+      "eval_steps_per_second": 1.453,
+      "step": 7500
     }
   ],
   "logging_steps": 500,
   "max_steps": 7500,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 8922744225792000.0,
+  "total_flos": 1.115343028224e+16,
   "trial_name": null,
   "trial_params": null
 }