Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fab01ab7058403f6dbea10e0ad99f0df3b760f20af6108d56aab095d23e7d2d
+oid sha256:6c6bc66d4b06be01722ead53718cdb38f760258e27b606dda260284c694f6516
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aa6a335295ee2a9b3f8c9947119c41c536718b44ea31c3861e075d1adee4761
+oid sha256:0d7efed836b0a7a09c864c26b9572f9547494689160dc13e5d77f14817033216
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a7c930eb0722d63a21f7f86c5859bca6cd7b20943a6e7ad39520b7053ae23d
+oid sha256:ae59f0f934189fcaa1a1041dd640da3c651fe2389123125ddf12471b0819bde8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c39a5eb5a9b85db1e545d7fe966a0dbc20c74269a76ea5b66d44f5c7e74d1aa6
+oid sha256:e82a21c3091e4958c484cdc7bf981ac78cd588dced7632b6352c65dac794dad2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7187402398550484,
   "best_model_checkpoint": "training_dir/checkpoint-10000",
-  "epoch": 1.0596587898696619,
+  "epoch": 1.165624668856628,
   "eval_steps": 1000,
-  "global_step": 10000,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -197,6 +197,25 @@
       "eval_samples_per_second": 87.848,
       "eval_steps_per_second": 10.981,
       "step": 10000
+    },
+    {
+      "epoch": 1.165624668856628,
+      "grad_norm": 5.598655700683594,
+      "learning_rate": 8.881431767337809e-06,
+      "loss": 0.3778,
+      "step": 11000
+    },
+    {
+      "epoch": 1.165624668856628,
+      "eval_accuracy": 0.7202797202797203,
+      "eval_f1": 0.7064609677451916,
+      "eval_loss": 1.072676420211792,
+      "eval_precision": 0.7267989053042323,
+      "eval_recall": 0.7202797202797203,
+      "eval_runtime": 26.0924,
+      "eval_samples_per_second": 87.688,
+      "eval_steps_per_second": 10.961,
+      "step": 11000
     }
   ],
   "logging_steps": 1000,
@@ -216,7 +235,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9707175033997104.0,
+  "total_flos": 1.0678923524708784e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null