Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97927bf58117b9f4ec7080fdbd5bd3da2e4d8230ad0fb35f5e8709b889bb2988
+oid sha256:67e81aecad78f65bf69252e47e81611b841ac0f01d0f85c90bf448e70f7470ee
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b0ec90550993f5bdeea2d600198f6e1e3e7da33644c6203a87be1e70067f33
+oid sha256:15c0ceedbd5b74cb19cb545e70335955cacec8ab258ee3e03d839c5d71b855a5
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e89c896d5de675a65aad5262ac3f12ebbd8dd5c6d70c67b825651cc5237f1b2
+oid sha256:f6edbde201324905f6602d4ac3a66a2f9df04374cec29badfe0ef7e38dacc7b2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbf5c0688e2287321a723c9f3d9f4506c43f1a47090333ea07799426904724fe
+oid sha256:3babaa29ea852e1ccade0b085c3362664b48b43dffc96f2a46a0dd0686d9e638
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3037343919277191,
-  "best_model_checkpoint": "./opt_trained/checkpoint-2576",
-  "epoch": 8.0,
+  "best_metric": 0.30269354581832886,
+  "best_model_checkpoint": "./opt_trained/checkpoint-2898",
+  "epoch": 9.0,
   "eval_steps": 500,
-  "global_step": 2576,
+  "global_step": 2898,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -106,6 +106,14 @@
       "eval_samples_per_second": 19.749,
       "eval_steps_per_second": 4.937,
       "step": 2576
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.30269354581832886,
+      "eval_runtime": 144.5227,
+      "eval_samples_per_second": 19.762,
+      "eval_steps_per_second": 4.94,
+      "step": 2898
     }
   ],
   "logging_steps": 500,
@@ -125,7 +133,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0742238019584e+17,
+  "total_flos": 1.2085017772032e+17,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null