Training in progress, step 18000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de7625f20d0dcc07edeedab2f5ad778c9eb054dc4595c9e3ceba5ea7791ad74f
+oid sha256:f9de62f5e3ac8fa3675164c064939053302d0982b52f6b9c9061fa8a4ea2e8e7
 size 1135685

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:097cb2603d2e93f7f90041a0ab13a04e882d220d6922888869e1a34176062ed9
+oid sha256:43807dea81ee99a02c493c399de34e7bc53c1e80ba5710c6e334e9ad1a473f51
 size 307910149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:379e82dd2c59802cee25bb7d5ed74b57d1427763dc05c8e296d69caa199aafc8
+oid sha256:75ad58ad0a403d074e295aa68981b411d541a4511d6b8ce5343ef9dd63d0470a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c7bfd871284a6faa92f94aee9c5ea71a9bdcdd13ee2b820e7d8b41939b332d
+oid sha256:62302b41ef27e8715d8b2f0e96943911ec884bb406e266f83a8ca9d79997b602
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": 1.7871696949005127,
   "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-label_and_explanation-selected-b64/checkpoint-2000",
-  "epoch": 1.8639328984156571,
-  "global_step": 16000,
+  "epoch": 2.096924510717614,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,11 +182,33 @@
       "eval_samples_per_second": 66.191,
       "eval_steps_per_second": 1.036,
       "step": 16000
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.0008319026830823564,
+      "loss": 1.046,
+      "step": 18000
+    },
+    {
+      "epoch": 2.1,
+      "eval_accuracy": 0.8814265393212761,
+      "eval_bertscore_f1": 0.933173856183393,
+      "eval_bleu": 0.4004651404942737,
+      "eval_f1": 0.8813416551856146,
+      "eval_loss": 1.8824745416641235,
+      "eval_rouge1": 0.609629583349967,
+      "eval_rouge2": 0.4060413051850321,
+      "eval_rougeL": 0.5545586773158176,
+      "eval_rougeLsum": 0.5564322531473485,
+      "eval_runtime": 157.9661,
+      "eval_samples_per_second": 62.304,
+      "eval_steps_per_second": 0.975,
+      "step": 18000
     }
   ],
   "max_steps": 85840,
   "num_train_epochs": 10,
-  "total_flos": 2.1933359341768704e+16,
+  "total_flos": 2.4686695794763776e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:097cb2603d2e93f7f90041a0ab13a04e882d220d6922888869e1a34176062ed9
+oid sha256:43807dea81ee99a02c493c399de34e7bc53c1e80ba5710c6e334e9ad1a473f51
 size 307910149