Training in progress, step 4800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7143fe76dbf46bf9442f8a1d204e06a2a81c24eeb986929fd120efb94de838a
+oid sha256:2ab00c9ddd34f1cf2964b1096db77b9d715fbc02bdd5c7d43b00066b8085e40d
 size 997351173

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9edb507618309c51118ca819a7d1a4dc21aced15d900dc58a9a3c689cecd7b17
+oid sha256:d45968dc773842b4524edf097410728d62c61752f13cc8b835d523befb79b605
 size 498665141

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43080b83229b77060a1c70537fc3b3d1446585e032227c6e29f72d1a997537c4
+oid sha256:ed4ae02de340745a578ad716a6dcb1ee42a03a56073f856062cfc5a83e2e3b94
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5f4434ed1f1c9d80d68b0f8157be0f9ddae46dd2e0f2023b9b90a13272136f7
+oid sha256:02d5d506efbd8a343664b3029e84353da8bd575421aff1c64d55aebab3313dcd
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.984626969048982,
-  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/roberta-base-e-snli-classification-nli_explanation-base/checkpoint-2800",
-  "epoch": 0.3727865796831314,
-  "global_step": 3200,
+  "best_metric": 0.9870629938253499,
+  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/roberta-base-e-snli-classification-nli_explanation-base/checkpoint-4800",
+  "epoch": 0.5591798695246971,
+  "global_step": 4800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -134,11 +134,75 @@
       "eval_samples_per_second": 2203.364,
       "eval_steps_per_second": 34.477,
       "step": 3200
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.054937867887508e-06,
+      "loss": 0.0822,
+      "step": 3600
+    },
+    {
+      "epoch": 0.42,
+      "eval_accuracy": 0.9861816703921967,
+      "eval_f1": 0.9861489775586069,
+      "eval_loss": 0.05556264892220497,
+      "eval_runtime": 4.7392,
+      "eval_samples_per_second": 2076.706,
+      "eval_steps_per_second": 32.495,
+      "step": 3600
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 8.891432308698496e-06,
+      "loss": 0.0764,
+      "step": 4000
+    },
+    {
+      "epoch": 0.47,
+      "eval_accuracy": 0.9852672221093274,
+      "eval_f1": 0.9852285614441253,
+      "eval_loss": 0.05288001894950867,
+      "eval_runtime": 4.2997,
+      "eval_samples_per_second": 2288.976,
+      "eval_steps_per_second": 35.816,
+      "step": 4000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 8.727926749509485e-06,
+      "loss": 0.0782,
+      "step": 4400
+    },
+    {
+      "epoch": 0.51,
+      "eval_accuracy": 0.9860800650274334,
+      "eval_f1": 0.9860421413180931,
+      "eval_loss": 0.05745375156402588,
+      "eval_runtime": 4.289,
+      "eval_samples_per_second": 2294.686,
+      "eval_steps_per_second": 35.905,
+      "step": 4400
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.564421190320473e-06,
+      "loss": 0.0722,
+      "step": 4800
+    },
+    {
+      "epoch": 0.56,
+      "eval_accuracy": 0.9870961186750661,
+      "eval_f1": 0.9870629938253499,
+      "eval_loss": 0.053428150713443756,
+      "eval_runtime": 4.4266,
+      "eval_samples_per_second": 2223.361,
+      "eval_steps_per_second": 34.789,
+      "step": 4800
     }
   ],
   "max_steps": 25752,
   "num_train_epochs": 3,
-  "total_flos": 8479257445588608.0,
+  "total_flos": 1.2774452433289344e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9edb507618309c51118ca819a7d1a4dc21aced15d900dc58a9a3c689cecd7b17
+oid sha256:d45968dc773842b4524edf097410728d62c61752f13cc8b835d523befb79b605
 size 498665141