Training in progress, step 12833, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0caaf2194e7c11f747141a29914d2c7311b23ecc790f8f7391591c8cf62b5fdc
+oid sha256:29b4c2ea257fabf9028ececdf5154335cb8dc30b703906e6c7ea4cba4f580074
 size 267906392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66b9e15d2567aa28604f83484a2dddda55b8d7a4563d4e9f37ba508020edb3f3
+oid sha256:586c9714380bf472baa0bfa318d091f90e9235ba0349d6d4a7848f42d276565d
 size 535874874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:714a88c6f44bf484acbe0664f5841b5c7784526e34bde08b3c5a79c600e45600
+oid sha256:710ca660e3d7c7135f44a01b4d42ea4e1a0aaeb5a3d565157ecb89c624206d60
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c04d7c7aee3cb0d767a512834acc784813a19d6669cbaf00a8719d470988f65d
+oid sha256:30fc97e3460c9f59b057d4ff3328764c986de4ec5f58edb05cef706aa6b9cabc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8291246891021729,
   "best_model_checkpoint": "/kaggle/working/results/checkpoint-10000",
-  "epoch": 0.9350892230967038,
+  "epoch": 1.0,
   "eval_steps": 1000,
-  "global_step": 12000,
+  "global_step": 12833,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -271,6 +271,13 @@
       "eval_samples_per_second": 104.206,
       "eval_steps_per_second": 0.822,
       "step": 12000
+    },
+    {
+      "epoch": 0.9740512740590664,
+      "grad_norm": 2.5609567165374756,
+      "learning_rate": 2.5948725940933534e-06,
+      "loss": 0.4517,
+      "step": 12500
     }
   ],
   "logging_steps": 500,
@@ -285,12 +292,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.0889252667392e+16,
+  "total_flos": 5.441783923385549e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null