Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6abbe53ad4bdac2acb6b66d420455cd29cb6827b7c717226acf69fa003615a2
+oid sha256:d31a90689bda13906c3d2b9014cf0f03ffe475ca00bd46cc5a89ef704c269aa2
 size 526442440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb66437cd1a1f3e85d760dae4101799dad85f6d2f44db58e8d2447de6ae42cdf
+oid sha256:ba95173fda6e5cd98497f7c742e0d43e56efc23513b8f1b8c8542a823a06881f
 size 1052723962

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90e807d11977312b0373d61c5dd72b09e491f95b6790237c43c227444a908b23
+oid sha256:9b4628423d479157682a147c925ad8913f28124292218dbe5f25553313c28d24
 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": 0.37554213404655457,
   "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": 536.767,
       "eval_steps_per_second": 13.443,
       "step": 863
+    },
+    {
+      "epoch": 1.1587485515643106,
+      "grad_norm": 1.1074819564819336,
+      "learning_rate": 3.0687524140594824e-05,
+      "loss": 0.2304,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7381228273464657,
+      "grad_norm": 1.0999990701675415,
+      "learning_rate": 2.103128621089224e-05,
+      "loss": 0.1765,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.3892330229282379,
+      "eval_runtime": 40.1411,
+      "eval_samples_per_second": 537.155,
+      "eval_steps_per_second": 13.453,
+      "step": 1726
     }
   ],
   "logging_steps": 500,
@@ -41,7 +63,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 821883496366080.0,
+  "total_flos": 1643766992732160.0,
   "train_batch_size": 40,
   "trial_name": null,
   "trial_params": null