Training in progress, step 20000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:668500daa8ad28ba1752adb76902631efe71bbfbbc7b58dc2a77ad0e0c886cc9
+oid sha256:b01dda222084cb93eb05b2e6c20c06fed23c63021cd951c94cb07dbe13654f1d
 size 1135685

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db8cdbb361aabc881d1114a73ac035104bb1e898fd8f7acd4145c5c89c907a5
+oid sha256:8aac42d97fe9656a51606d14104f9704a88e7cdc69f6a7fb6070b7b70a3fa494
 size 307910149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48fd37244d36e382ee4075e21f2271ce2b40181f69c1a4ed518bee64527c87ad
+oid sha256:74ff78922e2cb093754802d8057eed873e354abb062a4136f2587423e664e72d
 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": 1.692925214767456,
   "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-16000",
-  "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": 57.241,
       "eval_steps_per_second": 0.896,
       "step": 18000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 0.0008073772502084662,
+      "loss": 1.1764,
+      "step": 20000
+    },
+    {
+      "epoch": 2.33,
+      "eval_accuracy": null,
+      "eval_bertscore_f1": 0.9354710851566406,
+      "eval_bleu": 0.40988266787912037,
+      "eval_f1": null,
+      "eval_loss": 1.693483591079712,
+      "eval_rouge1": 0.6180761782666475,
+      "eval_rouge2": 0.41114120287967504,
+      "eval_rougeL": 0.5614112736943433,
+      "eval_rougeLsum": 0.5634652483896412,
+      "eval_runtime": 166.4526,
+      "eval_samples_per_second": 59.128,
+      "eval_steps_per_second": 0.925,
+      "step": 20000
     }
   ],
   "max_steps": 85840,
   "num_train_epochs": 10,
-  "total_flos": 2.720624988644352e+16,
+  "total_flos": 3.023965761482957e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db8cdbb361aabc881d1114a73ac035104bb1e898fd8f7acd4145c5c89c907a5
+oid sha256:8aac42d97fe9656a51606d14104f9704a88e7cdc69f6a7fb6070b7b70a3fa494
 size 307910149