Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:530ff1070ee72b249beda906bda92231486b86d9a947e9b503b2815575e4ccc5
+oid sha256:addd025876e116a312f6991474408559d0af0532e1b4f992b2addcef8bd5da87
 size 1681761380

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76ee868b7ed12f8b92ec4313553c693c3890c83d4867fdc24a44ec6b2eeeea51
+oid sha256:59fbc94c0ab809a212cd75928e528e2c49fce7db9666d6ead969abe7ec83d023
 size 3363321371

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35c014650e3c84b215306c3bf7757946cefea7c103430a269c3bbbc1c4778734
+oid sha256:ef7221890a7134ea2f5d764d71e45a50a5a07c68ebdc6724cddfcf18524c9c50
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dfae99b7c7eb9c1ab60d210efed69fa581dc2f02540b0acffc43b5e4c1c5aa0
+oid sha256:fbaf1fe07c08cae80261838683ae5bba41ac45905af686e74e6d05f19f13430d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.12665657699108124,
-  "best_model_checkpoint": "./vit5_qqp/checkpoint-3285",
-  "epoch": 1.0,
+  "best_metric": 0.11228575557470322,
+  "best_model_checkpoint": "./vit5_qqp/checkpoint-6570",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 3285,
+  "global_step": 6570,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -57,6 +57,63 @@
       "eval_samples_per_second": 70.312,
       "eval_steps_per_second": 1.956,
       "step": 3285
+    },
+    {
+      "epoch": 1.06544901065449,
+      "grad_norm": 0.3758560121059418,
+      "learning_rate": 3.224251648909183e-05,
+      "loss": 0.1228,
+      "step": 3500
+    },
+    {
+      "epoch": 1.21765601217656,
+      "grad_norm": 0.31075945496559143,
+      "learning_rate": 2.9705733130390666e-05,
+      "loss": 0.1052,
+      "step": 4000
+    },
+    {
+      "epoch": 1.36986301369863,
+      "grad_norm": 0.442830890417099,
+      "learning_rate": 2.71689497716895e-05,
+      "loss": 0.1044,
+      "step": 4500
+    },
+    {
+      "epoch": 1.5220700152207,
+      "grad_norm": 0.44427257776260376,
+      "learning_rate": 2.463216641298833e-05,
+      "loss": 0.1041,
+      "step": 5000
+    },
+    {
+      "epoch": 1.6742770167427703,
+      "grad_norm": 0.34879612922668457,
+      "learning_rate": 2.2095383054287164e-05,
+      "loss": 0.1025,
+      "step": 5500
+    },
+    {
+      "epoch": 1.82648401826484,
+      "grad_norm": 0.4718236029148102,
+      "learning_rate": 1.9558599695585997e-05,
+      "loss": 0.1007,
+      "step": 6000
+    },
+    {
+      "epoch": 1.9786910197869103,
+      "grad_norm": 0.4203096330165863,
+      "learning_rate": 1.702181633688483e-05,
+      "loss": 0.099,
+      "step": 6500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.11228575557470322,
+      "eval_runtime": 186.2342,
+      "eval_samples_per_second": 70.277,
+      "eval_steps_per_second": 1.955,
+      "step": 6570
     }
   ],
   "logging_steps": 500,
@@ -76,7 +133,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.50210369339392e+16,
+  "total_flos": 5.00420738678784e+16,
   "train_batch_size": 36,
   "trial_name": null,
   "trial_params": null