Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39c0c3e429059596e8f8f20164b6692dddc22cd098b352d3665253e5fdbcfc91
+oid sha256:7fab01ab7058403f6dbea10e0ad99f0df3b760f20af6108d56aab095d23e7d2d
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c01892709dc5774539f91fe55711e1975ef99a65bedc34693c03ce7c7bf9d37
+oid sha256:2aa6a335295ee2a9b3f8c9947119c41c536718b44ea31c3861e075d1adee4761
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5de4fbb1a4b28f7fc3108f426c0a660a8944f6d88933dbfb3727dcf48844484
+oid sha256:26a7c930eb0722d63a21f7f86c5859bca6cd7b20943a6e7ad39520b7053ae23d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fc78139ebcfada68990564fb6a028a79c77713a52b6e3d0b599cebfd1682acb
+oid sha256:c39a5eb5a9b85db1e545d7fe966a0dbc20c74269a76ea5b66d44f5c7e74d1aa6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7183207652218417,
-  "best_model_checkpoint": "training_dir/checkpoint-8000",
-  "epoch": 0.9536929108826958,
+  "best_metric": 0.7187402398550484,
+  "best_model_checkpoint": "training_dir/checkpoint-10000",
+  "epoch": 1.0596587898696619,
   "eval_steps": 1000,
-  "global_step": 9000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -178,6 +178,25 @@
       "eval_samples_per_second": 87.987,
       "eval_steps_per_second": 10.998,
       "step": 9000
+    },
+    {
+      "epoch": 1.0596587898696619,
+      "grad_norm": 10.622162818908691,
+      "learning_rate": 8.987962075210399e-06,
+      "loss": 0.4261,
+      "step": 10000
+    },
+    {
+      "epoch": 1.0596587898696619,
+      "eval_accuracy": 0.7242132867132867,
+      "eval_f1": 0.7187402398550484,
+      "eval_loss": 0.8997145295143127,
+      "eval_precision": 0.7327413713313974,
+      "eval_recall": 0.7242132867132867,
+      "eval_runtime": 26.0449,
+      "eval_samples_per_second": 87.848,
+      "eval_steps_per_second": 10.981,
+      "step": 10000
     }
   ],
   "logging_steps": 1000,
@@ -197,7 +216,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8735478289285824.0,
+  "total_flos": 9707175033997104.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null