Training in progress, step 20000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9de62f5e3ac8fa3675164c064939053302d0982b52f6b9c9061fa8a4ea2e8e7
+oid sha256:3846b3c29e47b11be970da1a78a3490b12d2fe2fa79e29be9b09160aee93105b
 size 1135685

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43807dea81ee99a02c493c399de34e7bc53c1e80ba5710c6e334e9ad1a473f51
+oid sha256:f4ee6c6ee6949afcc8336bdbc35656ca570a925c4cd835ede659ec5a93b70aa5
 size 307910149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75ad58ad0a403d074e295aa68981b411d541a4511d6b8ce5343ef9dd63d0470a
+oid sha256:0a7dcfad8f3ec7194138468fec9592f96ab4c360ce6e52e6d4c37c9e09920acd
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62302b41ef27e8715d8b2f0e96943911ec884bb406e266f83a8ca9d79997b602
+oid sha256:bf8a2c542f4369b40f2c9ac4520adbdd27d2fdf62e83a11bdbf824dc1f229fc2
 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": 2.096924510717614,
-  "global_step": 18000,
+  "epoch": 2.3299161230195713,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -204,11 +204,33 @@
       "eval_samples_per_second": 62.304,
       "eval_steps_per_second": 0.975,
       "step": 18000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 0.0008073772502084662,
+      "loss": 1.0175,
+      "step": 20000
+    },
+    {
+      "epoch": 2.33,
+      "eval_accuracy": 0.8784799837431416,
+      "eval_bertscore_f1": 0.9342269010537525,
+      "eval_bleu": 0.4055653781578464,
+      "eval_f1": 0.8790695152176341,
+      "eval_loss": 1.841552734375,
+      "eval_rouge1": 0.6082152523859634,
+      "eval_rouge2": 0.40038271576095896,
+      "eval_rougeL": 0.5521582299155425,
+      "eval_rougeLsum": 0.5539512056315703,
+      "eval_runtime": 145.4844,
+      "eval_samples_per_second": 67.65,
+      "eval_steps_per_second": 1.059,
+      "step": 20000
     }
   ],
   "max_steps": 85840,
   "num_train_epochs": 10,
-  "total_flos": 2.4686695794763776e+16,
+  "total_flos": 2.744212750967808e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43807dea81ee99a02c493c399de34e7bc53c1e80ba5710c6e334e9ad1a473f51
+oid sha256:f4ee6c6ee6949afcc8336bdbc35656ca570a925c4cd835ede659ec5a93b70aa5
 size 307910149