Training in progress, epoch 1

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 10.0,
     "eval_accuracy": 0.5270758122743683,
-    "eval_loss": 0.6930166482925415,
-    "eval_runtime": 0.2259,
+    "eval_loss": 0.7416719794273376,
+    "eval_runtime": 0.4617,
     "eval_samples": 277,
-    "eval_samples_per_second": 1226.394,
-    "eval_steps_per_second": 13.282,
-    "train_loss": 0.6997218401004106,
-    "train_runtime": 107.0767,
+    "eval_samples_per_second": 599.982,
+    "eval_steps_per_second": 6.498,
+    "train_loss": 0.7311154096554487,
+    "train_runtime": 165.3668,
     "train_samples": 2490,
-    "train_samples_per_second": 232.544,
-    "train_steps_per_second": 7.284
+    "train_samples_per_second": 150.574,
+    "train_steps_per_second": 4.717
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 10.0,
     "eval_accuracy": 0.5270758122743683,
-    "eval_loss": 0.6930166482925415,
-    "eval_runtime": 0.2259,
+    "eval_loss": 0.7416719794273376,
+    "eval_runtime": 0.4617,
     "eval_samples": 277,
-    "eval_samples_per_second": 1226.394,
-    "eval_steps_per_second": 13.282
+    "eval_samples_per_second": 599.982,
+    "eval_steps_per_second": 6.498
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28fed5edd19c436af8ed433d0035e7bc872331af016e2568ad589258b5118643
+oid sha256:bc154e75055ed4ffe4f6fee8eb3b2c83fd827575bcbab6fd3b65b47693d12588
 size 17106681

runs/Jan29_16-31-17_node4/events.out.tfevents.1643445112.node4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:925f4ba040aa6c9f84f7d17a5cbe0f9702e2a035bd097acdd1d164e18f03a5c1
-size 6252
+oid sha256:34c4a885f417543374c2a07f310166eabf93a8c508cd597d45e7a4374d07891c
+size 7252

runs/Jan29_16-31-17_node4/events.out.tfevents.1643445278.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:045861d11f65f7c6afb8a094b59dec9a6568396376aacdfcf159f4312a532cb4
+size 363

runs/Jan29_20-05-34_node4/1643457968.7279365/events.out.tfevents.1643457968.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:814290c69679ed43312ebbc0bf48a3f682052582af6282e7d933be52572006dd
+size 4585

runs/Jan29_20-05-34_node4/events.out.tfevents.1643457968.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25101b03c6a11388305cded96ccbe7445f5ef0d2c0c1d333c876738050ed0e2c
+size 3517

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
-    "train_loss": 0.6997218401004106,
-    "train_runtime": 107.0767,
+    "train_loss": 0.7311154096554487,
+    "train_runtime": 165.3668,
     "train_samples": 2490,
-    "train_samples_per_second": 232.544,
-    "train_steps_per_second": 7.284
+    "train_samples_per_second": 150.574,
+    "train_steps_per_second": 4.717
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_metric": 0.5270758122743683,
-  "best_model_checkpoint": "outputs/lora/roberta-base/v2/rte/checkpoint-234",
+  "best_model_checkpoint": "outputs/lora/roberta-base/v2/rte/checkpoint-312",
   "epoch": 10.0,
   "global_step": 780,
   "is_hyper_param_search": false,
@@ -10,112 +10,112 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7130928039550781,
-      "eval_runtime": 0.2073,
-      "eval_samples_per_second": 1336.057,
-      "eval_steps_per_second": 14.47,
+      "eval_loss": 0.755623996257782,
+      "eval_runtime": 0.4771,
+      "eval_samples_per_second": 580.569,
+      "eval_steps_per_second": 6.288,
       "step": 78
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6993798613548279,
-      "eval_runtime": 0.2002,
-      "eval_samples_per_second": 1383.767,
-      "eval_steps_per_second": 14.987,
+      "eval_loss": 0.822638988494873,
+      "eval_runtime": 0.4598,
+      "eval_samples_per_second": 602.409,
+      "eval_steps_per_second": 6.524,
       "step": 156
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6930166482925415,
-      "eval_runtime": 0.2199,
-      "eval_samples_per_second": 1259.694,
-      "eval_steps_per_second": 13.643,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7435575127601624,
+      "eval_runtime": 0.4678,
+      "eval_samples_per_second": 592.135,
+      "eval_steps_per_second": 6.413,
       "step": 234
     },
     {
       "epoch": 4.0,
       "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6923182606697083,
-      "eval_runtime": 0.201,
-      "eval_samples_per_second": 1378.119,
-      "eval_steps_per_second": 14.925,
+      "eval_loss": 0.7416719794273376,
+      "eval_runtime": 0.4671,
+      "eval_samples_per_second": 592.998,
+      "eval_steps_per_second": 6.422,
       "step": 312
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.696506917476654,
-      "eval_runtime": 0.2195,
-      "eval_samples_per_second": 1262.144,
-      "eval_steps_per_second": 13.669,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.694923996925354,
+      "eval_runtime": 0.4636,
+      "eval_samples_per_second": 597.536,
+      "eval_steps_per_second": 6.472,
       "step": 390
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6918743252754211,
-      "eval_runtime": 0.2123,
-      "eval_samples_per_second": 1304.889,
-      "eval_steps_per_second": 14.132,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7276150584220886,
+      "eval_runtime": 0.469,
+      "eval_samples_per_second": 590.599,
+      "eval_steps_per_second": 6.396,
       "step": 468
     },
     {
       "epoch": 6.41,
       "learning_rate": 0.001145975443383356,
-      "loss": 0.7031,
+      "loss": 0.7468,
       "step": 500
     },
     {
       "epoch": 7.0,
       "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6935069561004639,
-      "eval_runtime": 0.2336,
-      "eval_samples_per_second": 1185.748,
-      "eval_steps_per_second": 12.842,
+      "eval_loss": 0.7213642597198486,
+      "eval_runtime": 0.4575,
+      "eval_samples_per_second": 605.474,
+      "eval_steps_per_second": 6.557,
       "step": 546
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6938801407814026,
-      "eval_runtime": 0.2086,
-      "eval_samples_per_second": 1327.87,
-      "eval_steps_per_second": 14.381,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6917794942855835,
+      "eval_runtime": 0.4708,
+      "eval_samples_per_second": 588.418,
+      "eval_steps_per_second": 6.373,
       "step": 624
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6936783194541931,
-      "eval_runtime": 0.2108,
-      "eval_samples_per_second": 1313.785,
-      "eval_steps_per_second": 14.229,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.693771243095398,
+      "eval_runtime": 0.4588,
+      "eval_samples_per_second": 603.785,
+      "eval_steps_per_second": 6.539,
       "step": 702
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6938663125038147,
-      "eval_runtime": 0.2046,
-      "eval_samples_per_second": 1353.687,
-      "eval_steps_per_second": 14.661,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6928249597549438,
+      "eval_runtime": 0.4734,
+      "eval_samples_per_second": 585.163,
+      "eval_steps_per_second": 6.338,
       "step": 780
     },
     {
       "epoch": 10.0,
       "step": 780,
-      "total_flos": 1639048592332800.0,
-      "train_loss": 0.6997218401004106,
-      "train_runtime": 107.0767,
-      "train_samples_per_second": 232.544,
-      "train_steps_per_second": 7.284
+      "total_flos": 5862398439168000.0,
+      "train_loss": 0.7311154096554487,
+      "train_runtime": 165.3668,
+      "train_samples_per_second": 150.574,
+      "train_steps_per_second": 4.717
     }
   ],
   "max_steps": 780,
   "num_train_epochs": 10,
-  "total_flos": 1639048592332800.0,
+  "total_flos": 5862398439168000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3459cc4e350849119f9397e1e235b5df88dabf546417d4c780d5756a1941640
+oid sha256:5f4206444fbf1c81523734dcb23bd1a68f91cf3304eb6ee848e2f80495e87f03
 size 2991