Training in progress, step 13500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0269a233611aea2b93327f82cf53d8a46af1a81eed7742ab1bac2816b083a888
+oid sha256:262cba3b99f71731b09330abbe11713a01aa57fb06126a5fa85396b82e74ac81
 size 438032472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db0ea2d8a59372a77fd9592f1dd88308737bde985a99674df27bd5bcf23f288a
+oid sha256:80fc26a44b56e91180933edbd42d383c36444b4e4fea471c6a37bcebd23b040f
 size 876185914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6393ec11327fe7bbbbdf9c467a7c56a2343c2858aa9f5ba4c951fd9bca4b75d
+oid sha256:57bcecbeffb69d839dfb9027eecc5374273f4f897c54423646f7df0f98a033c9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d280452e93fed1dd4ebd6cabaa49557e6d8bc86b91d77f20fe573ed89665782
+oid sha256:ad041ddae909c27265965c75ca7aa3ce370785a5de1f06f1275ea8fa3539b886
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5394288301467896,
-  "best_model_checkpoint": "/kaggle/working/results/checkpoint-12500",
-  "epoch": 0.9411424020849924,
+  "best_metric": 0.5362756848335266,
+  "best_model_checkpoint": "/kaggle/working/results/checkpoint-13500",
+  "epoch": 0.977340186780569,
   "eval_steps": 500,
-  "global_step": 13000,
+  "global_step": 13500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -397,6 +397,21 @@
       "eval_samples_per_second": 63.866,
       "eval_steps_per_second": 0.499,
       "step": 13000
+    },
+    {
+      "epoch": 0.977340186780569,
+      "grad_norm": 7.781164169311523,
+      "learning_rate": 2.2659813219430974e-06,
+      "loss": 0.5288,
+      "step": 13500
+    },
+    {
+      "epoch": 0.977340186780569,
+      "eval_loss": 0.5362756848335266,
+      "eval_runtime": 122.2122,
+      "eval_samples_per_second": 63.823,
+      "eval_steps_per_second": 0.499,
+      "step": 13500
     }
   ],
   "logging_steps": 500,
@@ -416,7 +431,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.09477784911872e+17,
+  "total_flos": 1.13688468946944e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null