Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e88b1208748aef36d6d996074024d48213e091a6eac7b60f0aaed6a8a81fbd
+oid sha256:addd355e992f6e78ed27621e28b17033657a006cba1dcac6aeea15817818a40b
 size 267906392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85efd396b1b661411e1b698d0a9dcc469a983fe364de4301e305e6a5e5f944ba
+oid sha256:16795007535452604f213413ed041434f5641aac6ab96f594d9a0fd226faf965
 size 535874874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fe77dc62c9098928cae0a4055f5c14988a46413cd54eeacde8cd58584fa5fc1
+oid sha256:73c4e2cf6d267936a42dbe9231eba208b9eaf521e3d00c812c815687efe2b047
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:071c7071e26607643b9baa1a05c28cd720883bdbe388aad432c82437c94e7b69
+oid sha256:8f4da80fe7592d713534badf7928a6781e5f1fcca11df1350103327bd9824916
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4119344651699066,
   "best_model_checkpoint": "/kaggle/working/results/checkpoint-1000",
-  "epoch": 0.384948513136368,
+  "epoch": 0.43306707727841404,
   "eval_steps": 1000,
-  "global_step": 8000,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -183,6 +183,28 @@
       "eval_samples_per_second": 106.813,
       "eval_steps_per_second": 0.837,
       "step": 8000
+    },
+    {
+      "epoch": 0.409007795207391,
+      "grad_norm": 3.6804919242858887,
+      "learning_rate": 6.544124723318256e-05,
+      "loss": 0.4665,
+      "step": 8500
+    },
+    {
+      "epoch": 0.43306707727841404,
+      "grad_norm": 4.925282001495361,
+      "learning_rate": 6.929073236454625e-05,
+      "loss": 0.4483,
+      "step": 9000
+    },
+    {
+      "epoch": 0.43306707727841404,
+      "eval_loss": 0.4621144235134125,
+      "eval_runtime": 244.5245,
+      "eval_samples_per_second": 106.946,
+      "eval_steps_per_second": 0.838,
+      "step": 9000
     }
   ],
   "logging_steps": 500,
@@ -202,7 +224,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.3926168444928e+16,
+  "total_flos": 3.8166939500544e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null