Training in progress, step 15000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a51e5c274e6759482218b1a9949b06aaa0084e095225e121f04e074cdee3b5d
+oid sha256:31882bb59ace60deee154374a27b2586376c58b53c75d49fe8ef4f59d2735ff5
 size 438032472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:185eb7e0d70dd8683e519433b92665da245b53e81ea0fedb59d5efbc30ffd46e
+oid sha256:82e4b1cf021ca896eccee4933476e879cc09f7c7ffd7042ea35f89be59ff4e77
 size 876185978

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24fc33a64c66d2359c7f8585bd7346f3fdcff245a3033a9734ec1eeb41a538ee
+oid sha256:1f0d6edc6d5302a8346a12d9e6fe0565676124247fff5bdb99ce34f828f59ad4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22aa3bee8cb4a09eb99f41e952afb7bd82c1672b47992ef6737d79805582f3b4
+oid sha256:3e3306facb62f6002f7c25d4399b0fe1fa4166d62925b311563b72ad9931d0b9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.47014790773391724,
   "best_model_checkpoint": "results/checkpoint-14000",
-  "epoch": 0.964608834486429,
+  "epoch": 0.9978712080894092,
   "eval_steps": 500,
-  "global_step": 14500,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -442,6 +442,21 @@
       "eval_samples_per_second": 236.924,
       "eval_steps_per_second": 3.713,
       "step": 14500
+    },
+    {
+      "epoch": 0.9978712080894092,
+      "grad_norm": 5.323192596435547,
+      "learning_rate": 3.336881319850985e-05,
+      "loss": 0.4782,
+      "step": 15000
+    },
+    {
+      "epoch": 0.9978712080894092,
+      "eval_loss": 0.47367075085639954,
+      "eval_runtime": 44.5141,
+      "eval_samples_per_second": 233.634,
+      "eval_steps_per_second": 3.662,
+      "step": 15000
     }
   ],
   "logging_steps": 500,
@@ -461,7 +476,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.22109837017088e+17,
+  "total_flos": 1.2632052105216e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null