Training in progress, step 3200

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c42a5366840794b0c0fb0432bbaa031a842391943e8331fed713b5cd64f82ef1
+oid sha256:c7143fe76dbf46bf9442f8a1d204e06a2a81c24eeb986929fd120efb94de838a
 size 997351173

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e6bae183954f5d437ff9de22f8b455d34e8c948c4e9f409b7fdf25253e5efed
+oid sha256:9edb507618309c51118ca819a7d1a4dc21aced15d900dc58a9a3c689cecd7b17
 size 498665141

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55354db435c68678b6f94b24e84f2902d2393e19e425a5be089c34ccf6838fe5
+oid sha256:43080b83229b77060a1c70537fc3b3d1446585e032227c6e29f72d1a997537c4
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9ab84b3e9a31d3636ab888c3f3b4b43181ed71041b39e64d169f508e5b3f134
+oid sha256:a5f4434ed1f1c9d80d68b0f8157be0f9ddae46dd2e0f2023b9b90a13272136f7
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.983300542812346,
-  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/roberta-base-e-snli-classification-nli_explanation-base/checkpoint-2000",
-  "epoch": 0.23299161230195714,
-  "global_step": 2000,
+  "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,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -86,11 +86,59 @@
       "eval_samples_per_second": 2304.409,
       "eval_steps_per_second": 36.058,
       "step": 2000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.545454545454547e-06,
+      "loss": 0.0888,
+      "step": 2400
+    },
+    {
+      "epoch": 0.28,
+      "eval_accuracy": 0.983539930908352,
+      "eval_f1": 0.9834936652245868,
+      "eval_loss": 0.06838709861040115,
+      "eval_runtime": 4.2889,
+      "eval_samples_per_second": 2294.739,
+      "eval_steps_per_second": 35.906,
+      "step": 2400
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.381948986265533e-06,
+      "loss": 0.0833,
+      "step": 2800
+    },
+    {
+      "epoch": 0.33,
+      "eval_accuracy": 0.9846575899207478,
+      "eval_f1": 0.984626969048982,
+      "eval_loss": 0.05881618708372116,
+      "eval_runtime": 4.3142,
+      "eval_samples_per_second": 2281.283,
+      "eval_steps_per_second": 35.696,
+      "step": 2800
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.218443427076522e-06,
+      "loss": 0.0802,
+      "step": 3200
+    },
+    {
+      "epoch": 0.37,
+      "eval_accuracy": 0.9832351148140622,
+      "eval_f1": 0.9831849160413134,
+      "eval_loss": 0.06230289116501808,
+      "eval_runtime": 4.4668,
+      "eval_samples_per_second": 2203.364,
+      "eval_steps_per_second": 34.477,
+      "step": 3200
     }
   ],
   "max_steps": 25752,
   "num_train_epochs": 3,
-  "total_flos": 5305451844244608.0,
+  "total_flos": 8479257445588608.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e6bae183954f5d437ff9de22f8b455d34e8c948c4e9f409b7fdf25253e5efed
+oid sha256:9edb507618309c51118ca819a7d1a4dc21aced15d900dc58a9a3c689cecd7b17
 size 498665141