Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8d1313f274a21d0d8d09471175a9bd62427b83ff986e4d53c339e1e0ed1ebe4
+oid sha256:9ac48ef4d9be7da10a2675530a9c29dbe744b7066875fd8093f8f3925161228f
 size 1583480280

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f7103c19a3eeec8d178df723dd7add3a0d754ad342696f8bf8e3378c59f3b75
+oid sha256:50f03128116c85327f4a92b9502e6d5f025415604cca17d5c76bb781bdb19268
 size 3166950939

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef7221890a7134ea2f5d764d71e45a50a5a07c68ebdc6724cddfcf18524c9c50
+oid sha256:101b85eefdb57b4174f8e56178ff56799122c7abb93c7765f3d596841254b287
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbaf1fe07c08cae80261838683ae5bba41ac45905af686e74e6d05f19f13430d
+oid sha256:0e60debad2e0820d2d64238ae4a209b8d40fdcf351db5f0394509952de535c45
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.11589660495519638,
   "best_model_checkpoint": "./vit5_qqp/checkpoint-6570",
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 6570,
+  "global_step": 9855,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,48 @@
       "eval_samples_per_second": 73.171,
       "eval_steps_per_second": 2.035,
       "step": 6570
+    },
+    {
+      "epoch": 2.13089802130898,
+      "grad_norm": 0.3453280031681061,
+      "learning_rate": 1.4485032978183663e-05,
+      "loss": 0.101,
+      "step": 7000
+    },
+    {
+      "epoch": 2.2831050228310503,
+      "grad_norm": 0.3175284266471863,
+      "learning_rate": 1.1948249619482495e-05,
+      "loss": 0.097,
+      "step": 7500
+    },
+    {
+      "epoch": 2.43531202435312,
+      "grad_norm": 0.42786237597465515,
+      "learning_rate": 9.411466260781329e-06,
+      "loss": 0.0959,
+      "step": 8000
+    },
+    {
+      "epoch": 2.5875190258751903,
+      "grad_norm": 0.4301067590713501,
+      "learning_rate": 6.874682902080162e-06,
+      "loss": 0.095,
+      "step": 8500
+    },
+    {
+      "epoch": 2.73972602739726,
+      "grad_norm": 0.3909034729003906,
+      "learning_rate": 4.337899543378996e-06,
+      "loss": 0.0958,
+      "step": 9000
+    },
+    {
+      "epoch": 2.8919330289193304,
+      "grad_norm": 0.38906097412109375,
+      "learning_rate": 1.8011161846778284e-06,
+      "loss": 0.0939,
+      "step": 9500
     }
   ],
   "logging_steps": 500,
@@ -128,12 +170,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.00420738678784e+16,
+  "total_flos": 7.50631108018176e+16,
   "train_batch_size": 36,
   "trial_name": null,
   "trial_params": null