Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:486af49129a31e1b7c1e43e65eab8e26b8c4cc8ddc136711eef3f671ce00c3ec
+oid sha256:0caaf2194e7c11f747141a29914d2c7311b23ecc790f8f7391591c8cf62b5fdc
 size 267906392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bde14063113d3963bdceb328049937cf5555849d1cc907876d7f93ae43926358
+oid sha256:66b9e15d2567aa28604f83484a2dddda55b8d7a4563d4e9f37ba508020edb3f3
 size 535874874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbb2ca652b13d24cd9ca0437acca204dd7dc408e95308fc4b43867a99c53a4ed
+oid sha256:714a88c6f44bf484acbe0664f5841b5c7784526e34bde08b3c5a79c600e45600
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:058930117d0715c41bf93049e22ed1e989ddac193b68a49ee9225dc685ba128a
+oid sha256:c04d7c7aee3cb0d767a512834acc784813a19d6669cbaf00a8719d470988f65d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8291246891021729,
   "best_model_checkpoint": "/kaggle/working/results/checkpoint-10000",
-  "epoch": 0.7792410192472532,
+  "epoch": 0.9350892230967038,
   "eval_steps": 1000,
-  "global_step": 10000,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -227,6 +227,50 @@
       "eval_samples_per_second": 104.017,
       "eval_steps_per_second": 0.82,
       "step": 10000
+    },
+    {
+      "epoch": 0.8182030702096158,
+      "grad_norm": 2.9698691368103027,
+      "learning_rate": 1.8179692979038417e-05,
+      "loss": 0.4713,
+      "step": 10500
+    },
+    {
+      "epoch": 0.8571651211719785,
+      "grad_norm": 6.246368885040283,
+      "learning_rate": 1.4283487882802152e-05,
+      "loss": 0.4679,
+      "step": 11000
+    },
+    {
+      "epoch": 0.8571651211719785,
+      "eval_loss": 0.8628306984901428,
+      "eval_runtime": 49.8797,
+      "eval_samples_per_second": 104.251,
+      "eval_steps_per_second": 0.822,
+      "step": 11000
+    },
+    {
+      "epoch": 0.8961271721343411,
+      "grad_norm": 3.1601552963256836,
+      "learning_rate": 1.0387282786565886e-05,
+      "loss": 0.4565,
+      "step": 11500
+    },
+    {
+      "epoch": 0.9350892230967038,
+      "grad_norm": 2.656738758087158,
+      "learning_rate": 6.491077690329619e-06,
+      "loss": 0.4368,
+      "step": 12000
+    },
+    {
+      "epoch": 0.9350892230967038,
+      "eval_loss": 0.8968186378479004,
+      "eval_runtime": 49.901,
+      "eval_samples_per_second": 104.206,
+      "eval_steps_per_second": 0.822,
+      "step": 12000
     }
   ],
   "logging_steps": 500,
@@ -246,7 +290,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.240771055616e+16,
+  "total_flos": 5.0889252667392e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null