Training in progress, epoch 12, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:507e45593144bb2cf41c0598515e2ea5832f9e83502a991e35ca1fd8897d4b7b
+oid sha256:ea7fc909fdc3f1ae4015f0d4750a4a63b89ee5f2effb1be178a4a372ea6822ec
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08bee2e0984bbf63dd98e3afe5ce279648b51a871ad71dbaa9c855446f016deb
+oid sha256:e57e13a2fd122f2acccb2788d69aba473e357b7997bcdc0b72c1738b5c9421f2
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2816efc9f4c1de5a16c78e02f2554b79cf809e4fff588f530d63512ba1508099
+oid sha256:ee46d463575e74c9a732147771eadee45646a33c68ec6df02d9e322d868ddf4c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:667845ec98850da2da09c9709aecd8f85bd67e83fe7c6e52d5a2e2d27bb40110
+oid sha256:96a653363dc6a007bb7991143643fc45ea80be1e2dd1763a9221017fc9c83922
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9924370050430298,
-  "best_model_checkpoint": "./opt_trained/checkpoint-2211",
-  "epoch": 11.0,
+  "best_metric": 0.9905564785003662,
+  "best_model_checkpoint": "./opt_trained/checkpoint-2412",
+  "epoch": 12.0,
   "eval_steps": 500,
-  "global_step": 2211,
+  "global_step": 2412,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -123,6 +123,14 @@
       "eval_samples_per_second": 36.992,
       "eval_steps_per_second": 9.248,
       "step": 2211
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 0.9905564785003662,
+      "eval_runtime": 77.3311,
+      "eval_samples_per_second": 36.932,
+      "eval_steps_per_second": 9.233,
+      "step": 2412
     }
   ],
   "logging_steps": 500,
@@ -142,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.442986205952e+16,
+  "total_flos": 8.119621315584e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null