Training in progress, step 6000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffbab0fc63ce00717c302547e84f82da5c6ee76fb3265174a8133ebdecef1a17
+oid sha256:0e1d732c02e0feabfe1f578fffeed10ed4d202807175076a37cb7007ce570d65
 size 1135685

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:014b3be65b7ad8d2851782d7470f096709fe019b1add35f17e9f1ec11ff523c7
+oid sha256:3108f1190ef7767063f6f238e861136b4edb4fa997189d0ad1a8ef36bcd47c5e
 size 307910149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccf5e1fa7cb0e64b9f7031f08d5a7607e164e6d95900975a7b4d6e0b968b2a28
+oid sha256:789b5e5a77b520682f473ab0c74c6f4ab1c8d9e89b5ad86dd82c245c822a9464
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b61dc7ea15684027603ed37267a329167e46bc46091410e4d472ff753c910bd
+oid sha256:694564eb12c51c37ab71d88128d9bf8eb1f9e6023f1515525951d36307f22f25
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.7780297994613647,
-  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-2000",
-  "epoch": 0.4659832246039143,
-  "global_step": 4000,
+  "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": 0.6989748369058714,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -50,11 +50,33 @@
       "eval_samples_per_second": 60.18,
       "eval_steps_per_second": 0.942,
       "step": 4000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0009790552803256977,
+      "loss": 1.3804,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": null,
+      "eval_bertscore_f1": 0.9348857560079773,
+      "eval_bleu": 0.41900709929386093,
+      "eval_f1": null,
+      "eval_loss": 1.7246909141540527,
+      "eval_rouge1": 0.616316027086431,
+      "eval_rouge2": 0.4107303410412238,
+      "eval_rougeL": 0.5610382702035865,
+      "eval_rougeLsum": 0.5630504299315114,
+      "eval_runtime": 164.6404,
+      "eval_samples_per_second": 59.779,
+      "eval_steps_per_second": 0.935,
+      "step": 6000
     }
   ],
   "max_steps": 85840,
   "num_train_epochs": 10,
-  "total_flos": 6054128429826048.0,
+  "total_flos": 9074198514499584.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:014b3be65b7ad8d2851782d7470f096709fe019b1add35f17e9f1ec11ff523c7
+oid sha256:3108f1190ef7767063f6f238e861136b4edb4fa997189d0ad1a8ef36bcd47c5e
 size 307910149