Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c77661cf122b30a04f4aa6cd000dd6533ddd4353ab75c3d3d10d582b37f3b49d
+oid sha256:f17784ea5fb67c5913ce425ef6308b1353852a8e0c79a2174d95ed8cba70ae7f
 size 1681761380

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65a3cdefc8505797145911727202f35a8cdaeabfa9952d729a2ba3560541d9e7
+oid sha256:8bc52de097e9782e1e826f34ec13cf5024771b56821572ba62cd75ffcf6e08c9
 size 3363321371

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90929af1eba940155952091f85bda02adb1f6fd2b869f62220ba76e4e0de291c
+oid sha256:854c8f736a290926978c84338e8ea8816f0f1656561b7d42e716e67daa1a7464
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79a65e50ebd7c88e6afe05bce60e1437447659f0ab3d763f77217140057a93ad
+oid sha256:a7eaa191070e51793fbf344cd35501716ecc7578f20c1ced375c0d7bb5bee549
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4237809181213379,
   "best_model_checkpoint": "./vit5_qqp/checkpoint-863",
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 863,
+  "global_step": 1726,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22,6 +22,28 @@
       "eval_samples_per_second": 201.191,
       "eval_steps_per_second": 5.039,
       "step": 863
+    },
+    {
+      "epoch": 1.1587485515643106,
+      "grad_norm": 0.8257110714912415,
+      "learning_rate": 3.0687524140594824e-05,
+      "loss": 0.1866,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7381228273464657,
+      "grad_norm": 0.8043908476829529,
+      "learning_rate": 2.103128621089224e-05,
+      "loss": 0.1303,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4571397602558136,
+      "eval_runtime": 107.1835,
+      "eval_samples_per_second": 201.169,
+      "eval_steps_per_second": 5.038,
+      "step": 1726
     }
   ],
   "logging_steps": 500,
@@ -41,7 +63,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2628948507623424.0,
+  "total_flos": 5257897015246848.0,
   "train_batch_size": 40,
   "trial_name": null,
   "trial_params": null