Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9521d45ffde9e744a59ae0a218b76ee9dbb22362782eba61d3452f92bfb42ac
+oid sha256:d7f177ac17d529e29efb6e2c90b4fac1aac05de2d76cd0a83c56954cf8b22078
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb58efc731f5e9f91bb0a3b0b5d2ddd6631a24ee4477a9314d268b511c0900f3
+oid sha256:ed9d1686584d5775da006b6d922cf6c3eacb2065b66a18f07fbae7e722e33ba8
 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:bb7d986c9dd9650a7210dfcb89384b6f70fd4c8bf29e97d4befff946cb6fd316
+oid sha256:c54e76d8423a6511375b8501c7ed973174257694d1818266bf8544e0951cc13c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.29721641540527344,
   "best_model_checkpoint": "./opt_trained/checkpoint-2576",
-  "epoch": 8.0,
+  "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": 19.556,
       "eval_steps_per_second": 4.889,
       "step": 2576
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.29853811860084534,
+      "eval_runtime": 145.9347,
+      "eval_samples_per_second": 19.57,
+      "eval_steps_per_second": 4.893,
+      "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