Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68f16c9c25b89178636a661e8450dfcf3cf46b6ff0cff746b395f32896c46b62
+oid sha256:bc2887c0f115068dfe60a025aaf3ad207c18ab47143677d4167478267f6b3cba
 size 1583480280

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:574f141072a206040b849f9d39f0cee9a829150bbf8cbbf22bda4929c8773ca4
+oid sha256:9f1dc42c606e4428abbd85f4842da5c85465f1e7908759dcf76022e9bf9321bc
 size 3166950939

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:854c8f736a290926978c84338e8ea8816f0f1656561b7d42e716e67daa1a7464
+oid sha256:145074b3622966ab531c78b0530a9a56087ac77da546d1c877670db3a84669c7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7eaa191070e51793fbf344cd35501716ecc7578f20c1ced375c0d7bb5bee549
+oid sha256:46eebcd29db00a537bf14bf408f40eb76f139527a98e6a0ad7745886395731c6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.3348920941352844,
   "best_model_checkpoint": "./vit5_qqp/checkpoint-863",
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 1726,
+  "global_step": 2589,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,20 @@
       "eval_samples_per_second": 184.329,
       "eval_steps_per_second": 4.616,
       "step": 1726
+    },
+    {
+      "epoch": 2.317497103128621,
+      "grad_norm": 0.6376566886901855,
+      "learning_rate": 1.1375048281189648e-05,
+      "loss": 0.125,
+      "step": 2000
+    },
+    {
+      "epoch": 2.8968713789107765,
+      "grad_norm": 0.6937958598136902,
+      "learning_rate": 1.7188103514870608e-06,
+      "loss": 0.1083,
+      "step": 2500
     }
   ],
   "logging_steps": 500,
@@ -58,12 +72,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5842107794718720.0,
+  "total_flos": 8763161692078080.0,
   "train_batch_size": 40,
   "trial_name": null,
   "trial_params": null