Training in progress, step 800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77bb905d9236e55a1c8048367641832d0432d5423ec7cf04357b1b736054ee1a
+oid sha256:ca22e06e41773986bf4cda69e78b19dae8d6c06562e9f7bf57bb6bc359c523cd
 size 438032472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14512c44f1f37bd3c3d83693760eaaaba30f33ea26360258c85a62aec0a0ca30
+oid sha256:b50feb2e626b83408c0d4116c1f1ed25f6686b487bbb937489f8b52410e72e5a
 size 876185914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a703767195d880aff1d5c2dbc4d23286715c3798d1940a8fd2720bd4a5a675ff
+oid sha256:55b8d6aadceec387bdf2d000535b59c081063c48e8711fc23a19e65f0d3a3992
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51bb83752794024a27eef10009054d3313b178287743eebf62418a466a4bf8b4
+oid sha256:e22814798963634fbc95aa4159dff2ff1c962c3cd6bef60971d52789c5165d71
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2087372541427612,
-  "best_model_checkpoint": "/kaggle/working/results/checkpoint-600",
-  "epoch": 0.043437341634691956,
+  "best_metric": 1.1206928491592407,
+  "best_model_checkpoint": "/kaggle/working/results/checkpoint-800",
+  "epoch": 0.057916455512922606,
   "eval_steps": 200,
-  "global_step": 600,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -38,6 +38,14 @@
       "eval_samples_per_second": 63.757,
       "eval_steps_per_second": 0.499,
       "step": 600
+    },
+    {
+      "epoch": 0.057916455512922606,
+      "eval_loss": 1.1206928491592407,
+      "eval_runtime": 122.0821,
+      "eval_samples_per_second": 63.891,
+      "eval_steps_per_second": 0.5,
+      "step": 800
     }
   ],
   "logging_steps": 500,
@@ -57,7 +65,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5052820842086400.0,
+  "total_flos": 6737094456115200.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null