Training in progress, step 14000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc52c0fda0953e9c5a430c827e292d874b1f843ff7773931f9c93cc6008fe891
+oid sha256:a5a960b17798c7b8995ef1dc68fef82584cd48423ce850bd588f46544131a3c2
 size 1135685

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b2fe0ab2f310ff386ee37c2b5b780f689e9a8938176d4023a3a7ae780f91cae
+oid sha256:ff885e6aadd3d270b0e549f68ea1bd5fb91a649e29371ed75f3a8d66d517cf10
 size 307910149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8a619c5b75ad0de048a2974bf922da29a1e97a9cea67f262287c758eca45981
+oid sha256:98b1a0e8363bd62d636fdf22f594afac04c65df8c87bec6bc026af1848ed19a5
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f07e5c87a13181fdd91b70430838fde915aa2178a6a09686f68923b2683ae87
+oid sha256:9a9379299cb036bee8563adb6a6941350bd1a2187d737827bca0ce7b889d9885
 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": 1.3979496738117427,
-  "global_step": 12000,
+  "epoch": 1.6309412861136998,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -138,11 +138,33 @@
       "eval_samples_per_second": 64.983,
       "eval_steps_per_second": 1.017,
       "step": 12000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.0008809535488301369,
+      "loss": 1.0846,
+      "step": 14000
+    },
+    {
+      "epoch": 1.63,
+      "eval_accuracy": 0.8750254013411908,
+      "eval_bertscore_f1": 0.9330909099915095,
+      "eval_bleu": 0.39881326611406565,
+      "eval_f1": 0.875070205358106,
+      "eval_loss": 1.832938551902771,
+      "eval_rouge1": 0.6061633599628911,
+      "eval_rouge2": 0.39694115489567416,
+      "eval_rougeL": 0.550297473532996,
+      "eval_rougeLsum": 0.5523036866159814,
+      "eval_runtime": 154.4147,
+      "eval_samples_per_second": 63.737,
+      "eval_steps_per_second": 0.997,
+      "step": 14000
     }
   ],
   "max_steps": 85840,
   "num_train_epochs": 10,
-  "total_flos": 1.6445151317200896e+16,
+  "total_flos": 1.918701302527181e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b2fe0ab2f310ff386ee37c2b5b780f689e9a8938176d4023a3a7ae780f91cae
+oid sha256:ff885e6aadd3d270b0e549f68ea1bd5fb91a649e29371ed75f3a8d66d517cf10
 size 307910149