Training in progress, step 16000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b67a585ad731edfd3190139c2048716d1ef0cd5c4e23c5d039753733beb85292
+oid sha256:3a963e17d63c5311d4177c813a94a2aef757d599b9e54238d21dc7910cea8d38
 size 1135685

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:593e18bc3c456f313a1af17bb6a97030aabe3dfbde4c59f3e4ae0a040049cb77
+oid sha256:0ffb6cb62074cb556e4605433d13ffd9119d9af77cd667c007bfe11a29bc9c8a
 size 307910149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82960f07cae3e568bb93b45888fd2b6a63f1fd9b319bf6f6dda39789df0fc6a6
+oid sha256:e64fd0c22b4f678e997dcb527fccba5e7f7f0718a533bfc0e960d81e6c062ad4
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a9379299cb036bee8563adb6a6941350bd1a2187d737827bca0ce7b889d9885
+oid sha256:a3c7bfd871284a6faa92f94aee9c5ea71a9bdcdd13ee2b820e7d8b41939b332d
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.7180376052856445,
-  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-12000",
-  "epoch": 1.6309412861136998,
-  "global_step": 14000,
+  "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": 1.8639328984156571,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,11 +160,33 @@
       "eval_samples_per_second": 60.37,
       "eval_steps_per_second": 0.945,
       "step": 14000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.0008564281159562467,
+      "loss": 1.2367,
+      "step": 16000
+    },
+    {
+      "epoch": 1.86,
+      "eval_accuracy": null,
+      "eval_bertscore_f1": 0.9367065161642227,
+      "eval_bleu": 0.4269002075734853,
+      "eval_f1": null,
+      "eval_loss": 1.692925214767456,
+      "eval_rouge1": 0.6232036846315818,
+      "eval_rouge2": 0.4180000668098338,
+      "eval_rougeL": 0.5680648753273818,
+      "eval_rougeLsum": 0.570113733783007,
+      "eval_runtime": 165.5988,
+      "eval_samples_per_second": 59.433,
+      "eval_steps_per_second": 0.93,
+      "step": 16000
     }
   ],
   "max_steps": 85840,
   "num_train_epochs": 10,
-  "total_flos": 2.1150083559346176e+16,
+  "total_flos": 2.417528886921216e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:593e18bc3c456f313a1af17bb6a97030aabe3dfbde4c59f3e4ae0a040049cb77
+oid sha256:0ffb6cb62074cb556e4605433d13ffd9119d9af77cd667c007bfe11a29bc9c8a
 size 307910149