Training in progress, step 5200

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb078f66955011ea6afcb149ea16849afed6783f2a0810d9c8a62cd9a59686c5
+oid sha256:765ded4f85122106d3c7ca70ecc3286734cc83607e82caa135f0d00745a434b4
 size 2843230968

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:202a9040c68109cbb48b8fe2017897cfb1a7a3f10ba5d835b9cae6758ab0fd4f
+oid sha256:b58d358224de084112dd9ddc81a1e58fe3a83a78d808b5c279b4b2401d5f2b1f
 size 1421591285

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:778f07573f600fa48cbe5b11ab076696f67b51b6a5db2be2df0befcfb3b87a3b
+oid sha256:06744a746681eb14d92a4d87a2c4a3f33f8f040e9ff0c2cc0f5d538801039dce
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2beb2962f0b6cdb6d771bb320fa65eb0c0fa5a9c4fbb9b329b61e29cdbef62fe
+oid sha256:1785d5e671bc65a68d5c3dfbd2d502885b77ad2217c8d158cb3c228d55f0b090
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "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,
+  "best_metric": 0.9855364167633462,
+  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/roberta-large-e-snli-classification-nli_explanation-base-b16/checkpoint-4800",
+  "epoch": 0.15144454799627213,
+  "global_step": 5200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -118,11 +118,107 @@
       "eval_samples_per_second": 766.977,
       "eval_steps_per_second": 48.004,
       "step": 2800
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6.212385944476801e-06,
+      "loss": 0.1229,
+      "step": 3200
+    },
+    {
+      "epoch": 0.09,
+      "eval_accuracy": 0.9820158504369031,
+      "eval_f1": 0.9819483437268689,
+      "eval_loss": 0.10309657454490662,
+      "eval_runtime": 13.2533,
+      "eval_samples_per_second": 742.608,
+      "eval_steps_per_second": 46.479,
+      "step": 3200
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 6.988934187536401e-06,
+      "loss": 0.1291,
+      "step": 3600
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.9842511684616948,
+      "eval_f1": 0.9842093647131546,
+      "eval_loss": 0.08313809335231781,
+      "eval_runtime": 13.0051,
+      "eval_samples_per_second": 756.778,
+      "eval_steps_per_second": 47.366,
+      "step": 3600
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 7.765482430596002e-06,
+      "loss": 0.1049,
+      "step": 4000
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.9824222718959561,
+      "eval_f1": 0.9823847600112674,
+      "eval_loss": 0.0907953679561615,
+      "eval_runtime": 12.984,
+      "eval_samples_per_second": 758.01,
+      "eval_steps_per_second": 47.443,
+      "step": 4000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 8.542030673655602e-06,
+      "loss": 0.1243,
+      "step": 4400
+    },
+    {
+      "epoch": 0.13,
+      "eval_accuracy": 0.9823206665311929,
+      "eval_f1": 0.9822362137371193,
+      "eval_loss": 0.0925893783569336,
+      "eval_runtime": 12.9285,
+      "eval_samples_per_second": 761.262,
+      "eval_steps_per_second": 47.647,
+      "step": 4400
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.318578916715203e-06,
+      "loss": 0.1291,
+      "step": 4800
+    },
+    {
+      "epoch": 0.14,
+      "eval_accuracy": 0.9855720382036172,
+      "eval_f1": 0.9855364167633462,
+      "eval_loss": 0.08309133350849152,
+      "eval_runtime": 12.8482,
+      "eval_samples_per_second": 766.023,
+      "eval_steps_per_second": 47.945,
+      "step": 4800
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.994992693419992e-06,
+      "loss": 0.1148,
+      "step": 5200
+    },
+    {
+      "epoch": 0.15,
+      "eval_accuracy": 0.983946352367405,
+      "eval_f1": 0.9839146445196306,
+      "eval_loss": 0.08415436744689941,
+      "eval_runtime": 12.8411,
+      "eval_samples_per_second": 766.443,
+      "eval_steps_per_second": 47.971,
+      "step": 5200
     }
   ],
   "max_steps": 103008,
   "num_train_epochs": 3,
-  "total_flos": 5492559907900896.0,
+  "total_flos": 1.020890573605968e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:202a9040c68109cbb48b8fe2017897cfb1a7a3f10ba5d835b9cae6758ab0fd4f
+oid sha256:b58d358224de084112dd9ddc81a1e58fe3a83a78d808b5c279b4b2401d5f2b1f
 size 1421591285