Training in progress, step 1800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f8db643355ba94f446bdd2108b3ad40b89c4a17909a32d21478755e0770925c
+oid sha256:cf5eedaffdfa30482e714f831e7789ec7adabd5bf0475bdef3326ee344156f16
 size 2843228158

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26be059b9e3d553123dfe572fb1912a3e2fd6ab2703ff4d1787a0e42d6a5bd4c
+oid sha256:f65bf00ecada6d6f6b70b7db5964c0b3eb0b617f54e353d7314aa97df0133d3e
 size 1421588461

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1786c28a3ff60b9e5cc75072494414aab01774a7e1faabac2400987838a11166
+oid sha256:b5d43dde0c6d7da51ae34de8e125f82f70689f5e9858a0ddef8cfa60a79fee44
 size 14503

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f8f20db91521a631ff32f0f157e2cda744d77bd4375968aaad18f626c72d1c8
+oid sha256:7be3d111334799f516f34ca6adfa4185e3a4579faed68581da6d86666f61107e
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65de131eded300332b8d2247dfce2d1bcf678299231de832fceba967a9c4d776
+oid sha256:7f14c36be893ba57470539a7a5d2a8d5493e0e3009136b7c4dd8af472cd2b198
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.1649205985062833,
-  "best_model_checkpoint": "/home2/s5431786/nlp-final-project/results/roberta-large-e-snli-classification-nli-default/checkpoint-200",
-  "epoch": 0.011649580615097856,
-  "global_step": 200,
+  "best_metric": 0.9006977145472175,
+  "best_model_checkpoint": "/home2/s5431786/nlp-final-project/results/roberta-large-e-snli-classification-nli-default/checkpoint-1800",
+  "epoch": 0.1048462255358807,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22,11 +22,139 @@
       "eval_samples_per_second": 811.913,
       "eval_steps_per_second": 25.408,
       "step": 200
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.621653084982538e-06,
+      "loss": 0.9455,
+      "step": 400
+    },
+    {
+      "epoch": 0.02,
+      "eval_accuracy": 0.8268644584434058,
+      "eval_f1": 0.8266178743634524,
+      "eval_loss": 0.47128933668136597,
+      "eval_runtime": 12.689,
+      "eval_samples_per_second": 775.634,
+      "eval_steps_per_second": 24.273,
+      "step": 400
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.949941792782305e-06,
+      "loss": 0.4696,
+      "step": 600
+    },
+    {
+      "epoch": 0.03,
+      "eval_accuracy": 0.8723836618573461,
+      "eval_f1": 0.8706168205019141,
+      "eval_loss": 0.3847072422504425,
+      "eval_runtime": 12.9905,
+      "eval_samples_per_second": 757.631,
+      "eval_steps_per_second": 23.71,
+      "step": 600
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.278230500582073e-06,
+      "loss": 0.4354,
+      "step": 800
+    },
+    {
+      "epoch": 0.05,
+      "eval_accuracy": 0.8812233285917497,
+      "eval_f1": 0.881475018184628,
+      "eval_loss": 0.3468632698059082,
+      "eval_runtime": 12.7292,
+      "eval_samples_per_second": 773.183,
+      "eval_steps_per_second": 24.196,
+      "step": 800
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.915384143724325e-06,
+      "loss": 0.4001,
+      "step": 1000
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.8652712863239179,
+      "eval_f1": 0.8617608879520094,
+      "eval_loss": 0.3995899260044098,
+      "eval_runtime": 12.6196,
+      "eval_samples_per_second": 779.895,
+      "eval_steps_per_second": 24.406,
+      "step": 1000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.792752467962475e-06,
+      "loss": 0.3818,
+      "step": 1200
+    },
+    {
+      "epoch": 0.07,
+      "eval_accuracy": 0.8905710221499695,
+      "eval_f1": 0.8904945421102081,
+      "eval_loss": 0.34042540192604065,
+      "eval_runtime": 12.5333,
+      "eval_samples_per_second": 785.265,
+      "eval_steps_per_second": 24.574,
+      "step": 1200
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.670120792200626e-06,
+      "loss": 0.3577,
+      "step": 1400
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.8973785815891079,
+      "eval_f1": 0.8974465861723097,
+      "eval_loss": 0.30269765853881836,
+      "eval_runtime": 12.932,
+      "eval_samples_per_second": 761.059,
+      "eval_steps_per_second": 23.817,
+      "step": 1400
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.547489116438778e-06,
+      "loss": 0.3751,
+      "step": 1600
+    },
+    {
+      "epoch": 0.09,
+      "eval_accuracy": 0.8871164397480187,
+      "eval_f1": 0.8849187888163478,
+      "eval_loss": 0.33452147245407104,
+      "eval_runtime": 12.0676,
+      "eval_samples_per_second": 815.571,
+      "eval_steps_per_second": 25.523,
+      "step": 1600
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.424857440676928e-06,
+      "loss": 0.3471,
+      "step": 1800
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.9014427961796383,
+      "eval_f1": 0.9006977145472175,
+      "eval_loss": 0.27975374460220337,
+      "eval_runtime": 12.2016,
+      "eval_samples_per_second": 806.617,
+      "eval_steps_per_second": 25.243,
+      "step": 1800
     }
   ],
   "max_steps": 17168,
   "num_train_epochs": 1,
-  "total_flos": 569120757375168.0,
+  "total_flos": 5081780648726976.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26be059b9e3d553123dfe572fb1912a3e2fd6ab2703ff4d1787a0e42d6a5bd4c
+oid sha256:f65bf00ecada6d6f6b70b7db5964c0b3eb0b617f54e353d7314aa97df0133d3e
 size 1421588461