Training in progress, epoch 19, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66ebe755272c833ee429575beb043faa3e540a96844030cdd1171fc4cd696f08
+oid sha256:d2624e568b01117d2b53cb7c2188e6045c01a4fc93c512d290d0a67777429795
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:478c5c1c638d5d04267266ca64ac6928b413e616bc8f0af07f92f078e9ef68f5
+oid sha256:e74e67aa5ad57d75f3d0dcd7d8de37fe999a1e88db87fe66da4b00a4f5503669
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0b277510b0f644161ded5131086288f4993c9942ee7f089d0da5ae42603c16a
+oid sha256:bf46b4780f5a7b00f2a03861162972b05a45808ee3e2cef5e168534d2375ef68
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9c5a65300f8eb23ec040f2b45a372e7e707ff9400c5124bc4c052823f307128
+oid sha256:32464645d17632bf0c2e014289631964997d99b1535854552ce0dbdce65b6584
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3142348527908325,
-  "best_model_checkpoint": "./opt_trained/checkpoint-396",
-  "epoch": 18.0,
+  "best_metric": 1.3129278421401978,
+  "best_model_checkpoint": "./opt_trained/checkpoint-418",
+  "epoch": 19.0,
   "eval_steps": 500,
-  "global_step": 396,
+  "global_step": 418,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -151,6 +151,14 @@
       "eval_samples_per_second": 36.893,
       "eval_steps_per_second": 9.223,
       "step": 396
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 1.3129278421401978,
+      "eval_runtime": 8.1293,
+      "eval_samples_per_second": 36.903,
+      "eval_steps_per_second": 9.226,
+      "step": 418
     }
   ],
   "logging_steps": 500,
@@ -170,7 +178,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2769562068992e+16,
+  "total_flos": 1.3478982183936e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null