Training in progress, epoch 10, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e506e8b711532ffbf8d019c3dbaa09eaed27feabeff7810d601ccc9a23cfc2d9
+oid sha256:c4f7f3b258fbac6976842547331c3d48aa083028a135f498327e9df58911af32
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d0f82e522d7c9c2307fe7e6bb081646b7b91b63b1d6c1d5da80eb96ef27b786
+oid sha256:60d7668acdcfdb9a16eda03e9578b9cbc89b5a8aacb4cbd31ff3e99919b86217
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1812b24c4a0709c5ca3bbda05f6cbbac6be8f60609bcdd27c69d338fb9bf850d
+oid sha256:919692996631c0be3928e6f6b532de25918958ceafe3018cbd7af6262d2845df
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cf80e67dccb6aa983f190eabd4c5ec21d2397299a1f9709fdac00fd53b8aace
+oid sha256:e25903546b1ac2e6c22c5e02ff3e521f92aac9555ba1db8ec1a8b149df459618
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3414418697357178,
   "best_model_checkpoint": "./opt_trained/checkpoint-198",
-  "epoch": 9.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 198,
+  "global_step": 220,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -79,6 +79,14 @@
       "eval_samples_per_second": 37.245,
       "eval_steps_per_second": 9.311,
       "step": 198
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.3427915573120117,
+      "eval_runtime": 8.0486,
+      "eval_samples_per_second": 37.274,
+      "eval_steps_per_second": 9.318,
+      "step": 220
     }
   ],
   "logging_steps": 500,
@@ -98,7 +106,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6384781034496000.0,
+  "total_flos": 7094201149440000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null