Training in progress, step 12000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58691820f476a567a7509aeb201ddbf531c73f311c1fe52ed9507721ad2644cd
+oid sha256:ed334af45da6a372d4592aa75676cdb3e422acd36d6a0c66d955a1dbc57ab0dd
 size 1135685

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dbb7038a0f0645b0d66d337c43e0b2fc42278e08768249e5041d44350bdc159
+oid sha256:1021e377e391cc6947b7dce173c87b831be15e39b03af5b665c60dd6a202e167
 size 307910149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4f34ed6fb62f3e32f3b95ab6c580d66c7cd9f7bde80e675435ce41a6bf51932
+oid sha256:39405895ed2653446c0043563c21dc9b8fb85a36697b5b984761ec4ca5c49cff
 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": 1.7246909141540527,
-  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-6000",
-  "epoch": 1.1649580615097856,
-  "global_step": 10000,
+  "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": 1.3979496738117427,
+  "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": 59.156,
       "eval_steps_per_second": 0.926,
       "step": 10000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0009054789817040271,
+      "loss": 1.2598,
+      "step": 12000
+    },
+    {
+      "epoch": 1.4,
+      "eval_accuracy": null,
+      "eval_bertscore_f1": 0.9357474451383859,
+      "eval_bleu": 0.4237575236205067,
+      "eval_f1": null,
+      "eval_loss": 1.7180376052856445,
+      "eval_rouge1": 0.6178787224462856,
+      "eval_rouge2": 0.41096129012621224,
+      "eval_rougeL": 0.5625046403576894,
+      "eval_rougeLsum": 0.5643579355959574,
+      "eval_runtime": 161.2048,
+      "eval_samples_per_second": 61.053,
+      "eval_steps_per_second": 0.955,
+      "step": 12000
     }
   ],
   "max_steps": 85840,
   "num_train_epochs": 10,
-  "total_flos": 1.510371605809152e+16,
+  "total_flos": 1.8127294826041344e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dbb7038a0f0645b0d66d337c43e0b2fc42278e08768249e5041d44350bdc159
+oid sha256:1021e377e391cc6947b7dce173c87b831be15e39b03af5b665c60dd6a202e167
 size 307910149