Training in progress, step 7600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:765ded4f85122106d3c7ca70ecc3286734cc83607e82caa135f0d00745a434b4
+oid sha256:8c468bcf7bddaad4cfe5f21a8be06f85b469953475ff323261f94d5ccdb8a1e8
 size 2843230968

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b58d358224de084112dd9ddc81a1e58fe3a83a78d808b5c279b4b2401d5f2b1f
+oid sha256:3b80b7268d18e149e228859bf683e038919f218c78a06725456afb2efbd62075
 size 1421591285

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06744a746681eb14d92a4d87a2c4a3f33f8f040e9ff0c2cc0f5d538801039dce
+oid sha256:79a76a4ff38a22dd253bb22a59e6c5f070adba4b19d7ceb156911d72dbd948a2
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1785d5e671bc65a68d5c3dfbd2d502885b77ad2217c8d158cb3c228d55f0b090
+oid sha256:4eb81e4964c296ed1f062cf4a686cdaf7267fba5c8b0915f34103b8221211c4e
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "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,
+  "best_metric": 0.9861495731704059,
+  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/roberta-large-e-snli-classification-nli_explanation-base-b16/checkpoint-7200",
+  "epoch": 0.2213420316868593,
+  "global_step": 7600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -214,11 +214,107 @@
       "eval_samples_per_second": 766.443,
       "eval_steps_per_second": 47.971,
       "step": 5200
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.954116721338281e-06,
+      "loss": 0.1256,
+      "step": 5600
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.9836415362731152,
+      "eval_f1": 0.9836219614739408,
+      "eval_loss": 0.084382563829422,
+      "eval_runtime": 13.2723,
+      "eval_samples_per_second": 741.546,
+      "eval_steps_per_second": 46.413,
+      "step": 5600
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.91324074925657e-06,
+      "loss": 0.1207,
+      "step": 6000
+    },
+    {
+      "epoch": 0.17,
+      "eval_accuracy": 0.9829302987197724,
+      "eval_f1": 0.9829157443588743,
+      "eval_loss": 0.0957166850566864,
+      "eval_runtime": 12.9479,
+      "eval_samples_per_second": 760.125,
+      "eval_steps_per_second": 47.575,
+      "step": 6000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.872364777174857e-06,
+      "loss": 0.1162,
+      "step": 6400
+    },
+    {
+      "epoch": 0.19,
+      "eval_accuracy": 0.9859784596626702,
+      "eval_f1": 0.9859267481206228,
+      "eval_loss": 0.0752706453204155,
+      "eval_runtime": 13.005,
+      "eval_samples_per_second": 756.786,
+      "eval_steps_per_second": 47.366,
+      "step": 6400
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.831488805093147e-06,
+      "loss": 0.095,
+      "step": 6800
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.9844543791912213,
+      "eval_f1": 0.9844184876885574,
+      "eval_loss": 0.09373413771390915,
+      "eval_runtime": 13.0171,
+      "eval_samples_per_second": 756.082,
+      "eval_steps_per_second": 47.322,
+      "step": 6800
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.790612833011435e-06,
+      "loss": 0.1069,
+      "step": 7200
+    },
+    {
+      "epoch": 0.21,
+      "eval_accuracy": 0.9861816703921967,
+      "eval_f1": 0.9861495731704059,
+      "eval_loss": 0.07330357283353806,
+      "eval_runtime": 12.8964,
+      "eval_samples_per_second": 763.158,
+      "eval_steps_per_second": 47.765,
+      "step": 7200
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.749736860929725e-06,
+      "loss": 0.1054,
+      "step": 7600
+    },
+    {
+      "epoch": 0.22,
+      "eval_accuracy": 0.9853688274740906,
+      "eval_f1": 0.9853406697769191,
+      "eval_loss": 0.07271973788738251,
+      "eval_runtime": 12.8137,
+      "eval_samples_per_second": 768.085,
+      "eval_steps_per_second": 48.074,
+      "step": 7600
     }
   ],
   "max_steps": 103008,
   "num_train_epochs": 3,
-  "total_flos": 1.020890573605968e+16,
+  "total_flos": 1.4913660628723872e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b58d358224de084112dd9ddc81a1e58fe3a83a78d808b5c279b4b2401d5f2b1f
+oid sha256:3b80b7268d18e149e228859bf683e038919f218c78a06725456afb2efbd62075
 size 1421591285