Training in progress, step 2800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e47913498cc62e3d622e030fa2381e7512d18d5065ac931177b2dc5decc8f98
+oid sha256:fb078f66955011ea6afcb149ea16849afed6783f2a0810d9c8a62cd9a59686c5
 size 2843230968

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad67941a343ddab4739bbed3aafcbc93cf909ef47fa983f60de65a1f5efea2d
+oid sha256:202a9040c68109cbb48b8fe2017897cfb1a7a3f10ba5d835b9cae6758ab0fd4f
 size 1421591285

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8df2fbb5eae4ba8d93df3cabc2751ec21112d1099f8e59f83bee856092c76626
+oid sha256:778f07573f600fa48cbe5b11ab076696f67b51b6a5db2be2df0befcfb3b87a3b
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b5c0c9d70ab7582ef8cee0fb535ed73768bfc895b20793c16cf28f34c9dff83
+oid sha256:2beb2962f0b6cdb6d771bb320fa65eb0c0fa5a9c4fbb9b329b61e29cdbef62fe
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.7974911320075254,
-  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/roberta-large-e-snli-classification-nli_explanation-base-b16/checkpoint-400",
-  "epoch": 0.011649580615097856,
-  "global_step": 400,
+  "best_metric": 0.983181371856266,
+  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/roberta-large-e-snli-classification-nli_explanation-base-b16/checkpoint-2800",
+  "epoch": 0.081547064305685,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22,11 +22,107 @@
       "eval_samples_per_second": 764.91,
       "eval_steps_per_second": 47.875,
       "step": 400
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.5530964861192002e-06,
+      "loss": 0.3233,
+      "step": 800
+    },
+    {
+      "epoch": 0.02,
+      "eval_accuracy": 0.9642349116033326,
+      "eval_f1": 0.9642718853707861,
+      "eval_loss": 0.14329373836517334,
+      "eval_runtime": 12.933,
+      "eval_samples_per_second": 760.998,
+      "eval_steps_per_second": 47.63,
+      "step": 800
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.3296447291788007e-06,
+      "loss": 0.173,
+      "step": 1200
+    },
+    {
+      "epoch": 0.03,
+      "eval_accuracy": 0.9762243446453973,
+      "eval_f1": 0.9761597449883214,
+      "eval_loss": 0.1054357960820198,
+      "eval_runtime": 12.9969,
+      "eval_samples_per_second": 757.258,
+      "eval_steps_per_second": 47.396,
+      "step": 1200
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.1061929722384003e-06,
+      "loss": 0.1452,
+      "step": 1600
+    },
+    {
+      "epoch": 0.05,
+      "eval_accuracy": 0.9799837431416378,
+      "eval_f1": 0.9799316333368723,
+      "eval_loss": 0.09648650884628296,
+      "eval_runtime": 13.0065,
+      "eval_samples_per_second": 756.7,
+      "eval_steps_per_second": 47.361,
+      "step": 1600
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 3.882741215298001e-06,
+      "loss": 0.1449,
+      "step": 2000
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.9813046128835603,
+      "eval_f1": 0.9812341372941731,
+      "eval_loss": 0.09331633150577545,
+      "eval_runtime": 12.921,
+      "eval_samples_per_second": 761.706,
+      "eval_steps_per_second": 47.674,
+      "step": 2000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.659289458357601e-06,
+      "loss": 0.1303,
+      "step": 2400
+    },
+    {
+      "epoch": 0.07,
+      "eval_accuracy": 0.9815078236130867,
+      "eval_f1": 0.9814520761782233,
+      "eval_loss": 0.10890379548072815,
+      "eval_runtime": 12.8683,
+      "eval_samples_per_second": 764.824,
+      "eval_steps_per_second": 47.87,
+      "step": 2400
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 5.435837701417202e-06,
+      "loss": 0.1372,
+      "step": 2800
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.9832351148140622,
+      "eval_f1": 0.983181371856266,
+      "eval_loss": 0.07784133404493332,
+      "eval_runtime": 12.8322,
+      "eval_samples_per_second": 766.977,
+      "eval_steps_per_second": 48.004,
+      "step": 2800
     }
   ],
   "max_steps": 103008,
   "num_train_epochs": 3,
-  "total_flos": 792493810750848.0,
+  "total_flos": 5492559907900896.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad67941a343ddab4739bbed3aafcbc93cf909ef47fa983f60de65a1f5efea2d
+oid sha256:202a9040c68109cbb48b8fe2017897cfb1a7a3f10ba5d835b9cae6758ab0fd4f
 size 1421591285