Training in progress, step 22000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3846b3c29e47b11be970da1a78a3490b12d2fe2fa79e29be9b09160aee93105b
+oid sha256:519c0e4dec431c2c0f635bda86391a40186e90ed3223f4e553374a0732f8835a
 size 1135685

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4ee6c6ee6949afcc8336bdbc35656ca570a925c4cd835ede659ec5a93b70aa5
+oid sha256:7f8ae41cc27c39efd134f13937bdcf049711e63d2c142605c9a95ff9b9dbb3f1
 size 307910149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a7dcfad8f3ec7194138468fec9592f96ab4c360ce6e52e6d4c37c9e09920acd
+oid sha256:83eb951eaad067c8e35c930e1598ba4c2988926f2f41cb410ea47fa301451a75
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf8a2c542f4369b40f2c9ac4520adbdd27d2fdf62e83a11bdbf824dc1f229fc2
+oid sha256:00fc20b07457d2e67c7b293ab93cf0b2991ff2beeb6ad8da7e6a4999309dc031
 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": 2.3299161230195713,
-  "global_step": 20000,
+  "epoch": 2.562907735321528,
+  "global_step": 22000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -226,11 +226,33 @@
       "eval_samples_per_second": 67.65,
       "eval_steps_per_second": 1.059,
       "step": 20000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 0.000782851817334576,
+      "loss": 1.0166,
+      "step": 22000
+    },
+    {
+      "epoch": 2.56,
+      "eval_accuracy": 0.8834586466165414,
+      "eval_bertscore_f1": 0.9335280086325087,
+      "eval_bleu": 0.39913777987686355,
+      "eval_f1": 0.8834213943612278,
+      "eval_loss": 1.833051323890686,
+      "eval_rouge1": 0.6027866506270918,
+      "eval_rouge2": 0.39444299838413255,
+      "eval_rougeL": 0.5471957562329999,
+      "eval_rougeLsum": 0.5488406273419931,
+      "eval_runtime": 149.4283,
+      "eval_samples_per_second": 65.864,
+      "eval_steps_per_second": 1.031,
+      "step": 22000
     }
   ],
   "max_steps": 85840,
   "num_train_epochs": 10,
-  "total_flos": 2.744212750967808e+16,
+  "total_flos": 3.0178366029981696e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4ee6c6ee6949afcc8336bdbc35656ca570a925c4cd835ede659ec5a93b70aa5
+oid sha256:7f8ae41cc27c39efd134f13937bdcf049711e63d2c142605c9a95ff9b9dbb3f1
 size 307910149