Training in progress, step 42000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d193ff27c075191df41a8753d4124ffc0f8baafc06eba5ac95ed1ce740ce6ae
+oid sha256:79585244f2341bc92a811d0691afc68707fb0dda1b1ebf2f4da0268b317915b1
 size 1135685

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f3a7514a95f28ef73934da27d69c294765e4e757a4eadd4ef8b4aaccaa4f62c
+oid sha256:3ad4853b6740af17be6f97ec0dce8bf6ddeb7b59fae6c34b1d83b2a9472115d0
 size 307910149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79279175f3892ebfce7af0172b34a9afeaad2767a70562f1818d2115e3caa401
+oid sha256:4376fdf785551d2162440d20a0fc8c1333ccfea2017bf2464685b70bd9da04fa
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38c67dd5200a0105c5f2b1b8243a1ce46093d418497c730f1ff3a6d23cd097af
+oid sha256:cf6d9f4c1ec89d63c98b08543c58660f5818ed92d6babce2999c9131f7d6c72b
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "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": 4.659832246039143,
-  "global_step": 40000,
+  "epoch": 4.8928238583410995,
+  "global_step": 42000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -446,11 +446,33 @@
       "eval_samples_per_second": 59.685,
       "eval_steps_per_second": 0.934,
       "step": 40000
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 0.0005375974885956737,
+      "loss": 1.0858,
+      "step": 42000
+    },
+    {
+      "epoch": 4.89,
+      "eval_accuracy": null,
+      "eval_bertscore_f1": 0.9373510686986889,
+      "eval_bleu": 0.432049715666974,
+      "eval_f1": null,
+      "eval_loss": 1.7263308763504028,
+      "eval_rouge1": 0.6324147183021485,
+      "eval_rouge2": 0.42847933630650004,
+      "eval_rougeL": 0.5752177231277784,
+      "eval_rougeLsum": 0.5770958516370777,
+      "eval_runtime": 161.8865,
+      "eval_samples_per_second": 60.796,
+      "eval_steps_per_second": 0.951,
+      "step": 42000
     }
   ],
   "max_steps": 85840,
   "num_train_epochs": 10,
-  "total_flos": 6.045034099950797e+16,
+  "total_flos": 6.348007739042611e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f3a7514a95f28ef73934da27d69c294765e4e757a4eadd4ef8b4aaccaa4f62c
+oid sha256:3ad4853b6740af17be6f97ec0dce8bf6ddeb7b59fae6c34b1d83b2a9472115d0
 size 307910149