Training in progress, step 28000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf0a7e66c07cedbfa7a6f533a63696eb1e50f06c16cd6d73731a57befdc52ece
+oid sha256:edbe5216af631064366ecf05aa534ad20c366a263b1f8db439aab89dbdc2e625
 size 1135685

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b74a162c61e55614ed9eb2677d7694de994a1c375b65e4178befa43b29b1d49
+oid sha256:aef5709eb31a08c0cdd81aa3dbc6eefb09d41a893a697e68b1683c2cbd182943
 size 307910149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5db5a92bb996eb3fcc170f894aa71fe532ff0c6149a5a76e554e4e7f285a0bb
+oid sha256:9f0bfa8ad16ddcd2952ce9bb8289d098e1f99960c76a9912c6bb28bd96e0e0cb
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a11e5c174a0a481c5093560eac3ef77d341871a0e1df788ef5246aa276c5707f
+oid sha256:2205f7ae4e05695eaa6f3999cd90337ec1f041934d0888712b6d545d3628b23a
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.692925214767456,
-  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-16000",
-  "epoch": 3.0288909599254428,
-  "global_step": 26000,
+  "best_metric": 1.6879340410232544,
+  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-28000",
+  "epoch": 3.2618825722273996,
+  "global_step": 28000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -292,11 +292,33 @@
       "eval_samples_per_second": 59.635,
       "eval_steps_per_second": 0.933,
       "step": 26000
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 0.0007092755187129053,
+      "loss": 1.1213,
+      "step": 28000
+    },
+    {
+      "epoch": 3.26,
+      "eval_accuracy": null,
+      "eval_bertscore_f1": 0.9357226263202562,
+      "eval_bleu": 0.4211338041409779,
+      "eval_f1": null,
+      "eval_loss": 1.6879340410232544,
+      "eval_rouge1": 0.6241785396960564,
+      "eval_rouge2": 0.4172784618159209,
+      "eval_rougeL": 0.5676477480665587,
+      "eval_rougeLsum": 0.5698542368429731,
+      "eval_runtime": 161.3196,
+      "eval_samples_per_second": 61.009,
+      "eval_steps_per_second": 0.955,
+      "step": 28000
     }
   ],
   "max_steps": 85840,
   "num_train_epochs": 10,
-  "total_flos": 3.929051016988877e+16,
+  "total_flos": 4.230446910422016e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b74a162c61e55614ed9eb2677d7694de994a1c375b65e4178befa43b29b1d49
+oid sha256:aef5709eb31a08c0cdd81aa3dbc6eefb09d41a893a697e68b1683c2cbd182943
 size 307910149