Training in progress, step 12000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7a5e153b4a276c51311015ef7d32b4608d62762f7513236318a1ba50af8e70f
+oid sha256:4a54a4a31b31cbcad9e386403f783c66ac5d7abbe7f401c23658bb39c407bbe9
 size 1135685

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e1f86e5ed9d088634a6c5c4549647aa229ec662b65d4a8392219025744cf3c1
+oid sha256:09d3138a7165d438b83836834da671edfe79b107ed24189658714a9b794d36db
 size 307910149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c81298488a17e1b0ae49686ebcf93f90fd3c0a99ff00d5fb11e63f22f7814a35
+oid sha256:d1ec407948436ccc80e93f11a93c1f5e1ff6f5e9d21d8a10b12885e1b8426660
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e2630ad918c61bc51cc3ab06f53d7b1174e5ad20efe090354e938c18819c227
+oid sha256:8768affab55180e629d6c31ff86e7291be472952121ca2693615f1bb55de2777
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": 1.748366355895996,
   "best_model_checkpoint": "/home2/s5432073/nlp-final-project/results/google-flan-t5-small-e-snli-generation-label_and_explanation-selected-b48/checkpoint-2000",
-  "epoch": 0.8736676568233444,
-  "global_step": 10000,
+  "epoch": 1.0484011881880133,
+  "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": 57.474,
       "eval_steps_per_second": 1.203,
       "step": 10000
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0009422735591381039,
+      "loss": 1.1371,
+      "step": 12000
+    },
+    {
+      "epoch": 1.05,
+      "eval_accuracy": 0.8622231253810201,
+      "eval_bertscore_f1": 0.9329314648717478,
+      "eval_bleu": 0.40472213589689604,
+      "eval_f1": 0.8623314280769628,
+      "eval_loss": 1.871994137763977,
+      "eval_rouge1": 0.605873896307076,
+      "eval_rouge2": 0.398828693131973,
+      "eval_rougeL": 0.5475319717542413,
+      "eval_rougeLsum": 0.5495598969128583,
+      "eval_runtime": 154.2147,
+      "eval_samples_per_second": 63.82,
+      "eval_steps_per_second": 1.336,
+      "step": 12000
     }
   ],
   "max_steps": 114460,
   "num_train_epochs": 10,
-  "total_flos": 9877739266473984.0,
+  "total_flos": 1.1869746997825536e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e1f86e5ed9d088634a6c5c4549647aa229ec662b65d4a8392219025744cf3c1
+oid sha256:09d3138a7165d438b83836834da671edfe79b107ed24189658714a9b794d36db
 size 307910149