Training in progress, epoch 18, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e17c1b54e6213a55c53215444b25ee79cc33e9ad7702a6cbb6e16edb930d80d
+oid sha256:2d904cffa369ce78e9119398130865ac1f3996bb8bece1055f5f2daa489ac182
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be4183eebbd4d3837bb0ce569467624969618a02d0e02d3d700c44c4caf20c7e
+oid sha256:54b70f88e3151cf84c48f5046c57cac2d1ff2f2133ec5aec054cc5bfdb62d15b
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e01898925b7af5f5ba289c8fef21f79a7a00ffbf1a0745625b200f27c799885
+oid sha256:42f911a18aa88e5fc007b16c9fbc080cc2b3442d104073ff1531c7a039f0d2ff
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0295287d39e8a510b3de0550fdcbbb67b482b2d7bf41ccc76c3e4cfea285df7d
+oid sha256:a85f1876797cb445e24128c5e2e6a14438742060f3fca2893fbd8ffa09da69f4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.9877104163169861,
   "best_model_checkpoint": "./opt_trained/checkpoint-3216",
-  "epoch": 17.0,
+  "epoch": 18.0,
   "eval_steps": 500,
-  "global_step": 3417,
+  "global_step": 3618,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -185,6 +185,21 @@
       "eval_samples_per_second": 37.171,
       "eval_steps_per_second": 9.293,
       "step": 3417
+    },
+    {
+      "epoch": 17.413449564134496,
+      "grad_norm": 1.899855136871338,
+      "learning_rate": 5.0100000000000005e-05,
+      "loss": 0.9154,
+      "step": 3500
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 0.9950315952301025,
+      "eval_runtime": 76.8254,
+      "eval_samples_per_second": 37.175,
+      "eval_steps_per_second": 9.294,
+      "step": 3618
     }
   ],
   "logging_steps": 500,
@@ -204,7 +219,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1502796863744e+17,
+  "total_flos": 1.2179431973376e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null