Training in progress, step 12000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dcf1e089fce6094a43a6df148dccae971c0758feecdb68eeeb7dc88e615426f
+oid sha256:fc52c0fda0953e9c5a430c827e292d874b1f843ff7773931f9c93cc6008fe891
 size 1135685

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f0978cde5847e3dd7ce8a7f7c7c3254251303630f4b6281edb8558cea3d3d29
+oid sha256:6b2fe0ab2f310ff386ee37c2b5b780f689e9a8938176d4023a3a7ae780f91cae
 size 307910149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40593ea88f5e9169b2d59cd6aa5b2cd985839724b0346e888aae95e4bdf14a75
+oid sha256:f8a619c5b75ad0de048a2974bf922da29a1e97a9cea67f262287c758eca45981
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71a546360b22b38e65568c028955da704276b3a9551ee9dcac6165cd80d1258c
+oid sha256:7f07e5c87a13181fdd91b70430838fde915aa2178a6a09686f68923b2683ae87
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": 1.7871696949005127,
   "best_model_checkpoint": "/home2/s5432073/nlp-final-project/results/google-flan-t5-small-e-snli-generation-label_and_explanation-selected-b64/checkpoint-2000",
-  "epoch": 1.1649580615097856,
-  "global_step": 10000,
+  "epoch": 1.3979496738117427,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -116,11 +116,33 @@
       "eval_samples_per_second": 66.314,
       "eval_steps_per_second": 1.038,
       "step": 10000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0009054789817040271,
+      "loss": 1.0913,
+      "step": 12000
+    },
+    {
+      "epoch": 1.4,
+      "eval_accuracy": 0.8691322901849218,
+      "eval_bertscore_f1": 0.9338201113503969,
+      "eval_bleu": 0.4012059786299585,
+      "eval_f1": 0.8686267742768865,
+      "eval_loss": 1.870266079902649,
+      "eval_rouge1": 0.6062872493545299,
+      "eval_rouge2": 0.39947246134905595,
+      "eval_rougeL": 0.5500107773403655,
+      "eval_rougeLsum": 0.5520562338476832,
+      "eval_runtime": 149.6673,
+      "eval_samples_per_second": 65.759,
+      "eval_steps_per_second": 1.029,
+      "step": 12000
     }
   ],
   "max_steps": 85840,
   "num_train_epochs": 10,
-  "total_flos": 1.3703196663877632e+16,
+  "total_flos": 1.6445151317200896e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f0978cde5847e3dd7ce8a7f7c7c3254251303630f4b6281edb8558cea3d3d29
+oid sha256:6b2fe0ab2f310ff386ee37c2b5b780f689e9a8938176d4023a3a7ae780f91cae
 size 307910149