Training in progress, step 6000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ab00c9ddd34f1cf2964b1096db77b9d715fbc02bdd5c7d43b00066b8085e40d
+oid sha256:8228de27106e44527ce87d66105e3205dc6540a551e7cca8525ac6fda3a5396f
 size 997351173

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d45968dc773842b4524edf097410728d62c61752f13cc8b835d523befb79b605
+oid sha256:2668a06099ffd93fb8a66976b2bedf58dc654e44d146913529cbbe24d18cf2f0
 size 498665141

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed4ae02de340745a578ad716a6dcb1ee42a03a56073f856062cfc5a83e2e3b94
+oid sha256:b6d8e09ceae8c97b30c879d0a88b02e5d6f9d2c8f95483bbc40029b8fbdfe781
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d5d506efbd8a343664b3029e84353da8bd575421aff1c64d55aebab3313dcd
+oid sha256:21d2ce5a39857d286d2308d95541d019234b54f63ac7ba9f37f9448c047c7cc8
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "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,
+  "epoch": 0.6989748369058714,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,11 +198,59 @@
       "eval_samples_per_second": 2223.361,
       "eval_steps_per_second": 34.789,
       "step": 4800
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.40091563113146e-06,
+      "loss": 0.071,
+      "step": 5200
+    },
+    {
+      "epoch": 0.61,
+      "eval_accuracy": 0.985876854297907,
+      "eval_f1": 0.9858488466773426,
+      "eval_loss": 0.0532599538564682,
+      "eval_runtime": 4.3538,
+      "eval_samples_per_second": 2260.534,
+      "eval_steps_per_second": 35.371,
+      "step": 5200
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.237410071942446e-06,
+      "loss": 0.0723,
+      "step": 5600
+    },
+    {
+      "epoch": 0.65,
+      "eval_accuracy": 0.9860800650274334,
+      "eval_f1": 0.9860406491659012,
+      "eval_loss": 0.04955599084496498,
+      "eval_runtime": 4.2895,
+      "eval_samples_per_second": 2294.439,
+      "eval_steps_per_second": 35.902,
+      "step": 5600
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 8.073904512753434e-06,
+      "loss": 0.0713,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.9860800650274334,
+      "eval_f1": 0.9860488223249062,
+      "eval_loss": 0.051210932433605194,
+      "eval_runtime": 4.2586,
+      "eval_samples_per_second": 2311.113,
+      "eval_steps_per_second": 36.163,
+      "step": 6000
     }
   ],
   "max_steps": 25752,
   "num_train_epochs": 3,
-  "total_flos": 1.2774452433289344e+16,
+  "total_flos": 1.597164223963392e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d45968dc773842b4524edf097410728d62c61752f13cc8b835d523befb79b605
+oid sha256:2668a06099ffd93fb8a66976b2bedf58dc654e44d146913529cbbe24d18cf2f0
 size 498665141