Training in progress, epoch 8, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b25316505855cf494267aec09fdf57c4bff22da2b10f3795d92c589993260e93
+oid sha256:97927bf58117b9f4ec7080fdbd5bd3da2e4d8230ad0fb35f5e8709b889bb2988
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e5738f832083a74182d5df41d22d89c5a5617631cbcb54e511ee4c079370d48
+oid sha256:a9b0ec90550993f5bdeea2d600198f6e1e3e7da33644c6203a87be1e70067f33
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ed244f721b9495a7585428e681f68fc58fe0408c52158c97e3cc0c7c1263a36
+oid sha256:5e89c896d5de675a65aad5262ac3f12ebbd8dd5c6d70c67b825651cc5237f1b2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8ac4a1a7643d89921844755fac4df06257bb3227bbdd9eeb1bf3815ec0f7345
+oid sha256:bbf5c0688e2287321a723c9f3d9f4506c43f1a47090333ea07799426904724fe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.30498865246772766,
-  "best_model_checkpoint": "./opt_trained/checkpoint-2254",
-  "epoch": 7.0,
+  "best_metric": 0.3037343919277191,
+  "best_model_checkpoint": "./opt_trained/checkpoint-2576",
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 2254,
+  "global_step": 2576,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,21 @@
       "eval_samples_per_second": 19.744,
       "eval_steps_per_second": 4.936,
       "step": 2254
+    },
+    {
+      "epoch": 7.765758754863813,
+      "grad_norm": 2.2369720935821533,
+      "learning_rate": 3.054517133956387e-05,
+      "loss": 0.3023,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.3037343919277191,
+      "eval_runtime": 144.6161,
+      "eval_samples_per_second": 19.749,
+      "eval_steps_per_second": 4.937,
+      "step": 2576
     }
   ],
   "logging_steps": 500,
@@ -110,7 +125,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.399458267136e+16,
+  "total_flos": 1.0742238019584e+17,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null