Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97477183783427f4a0e6c4c64c89c2ff713711937ba50a0a7f0ebc2c0beb19eb
+oid sha256:78c9e820e6f2b34afef294ea03b9806ca31e36f8873e0df7c298ce3b6bdee8fd
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e3b341e9e13369ba57399436690c86adca73b7a520cae93fbc7be3f277f55d6
+oid sha256:611e8a5f53f98861b9122353f39089365a355506c0f560578945807b4e4b391f
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04491054115f5fca09d38960caedd814323b1326ebd99907da9bf3fbd799e184
+oid sha256:40c6f4b43aefb772d54e56c245109d4d777d2195b3fa9ce39aa759919ebd5a69
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20335469f0ec66a4e6ceae2c6f0f5a5eb0bddc566fe7b367e2d26bc30cb02212
+oid sha256:82489f346a442f6da6a913d4059284e68bce2bb5b3b04d85ed6e18e1fb87da9f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7023119335505582,
-  "best_model_checkpoint": "training_dir/checkpoint-7000",
-  "epoch": 0.7417611529087634,
+  "best_metric": 0.7183207652218417,
+  "best_model_checkpoint": "training_dir/checkpoint-8000",
+  "epoch": 0.8477270318957296,
   "eval_steps": 1000,
-  "global_step": 7000,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -140,6 +140,25 @@
       "eval_samples_per_second": 87.878,
       "eval_steps_per_second": 10.985,
       "step": 7000
+    },
+    {
+      "epoch": 0.8477270318957296,
+      "grad_norm": 7.15505838394165,
+      "learning_rate": 9.201022690955577e-06,
+      "loss": 0.4598,
+      "step": 8000
+    },
+    {
+      "epoch": 0.8477270318957296,
+      "eval_accuracy": 0.7263986013986014,
+      "eval_f1": 0.7183207652218417,
+      "eval_loss": 0.782526969909668,
+      "eval_precision": 0.7270872567100993,
+      "eval_recall": 0.7263986013986014,
+      "eval_runtime": 26.0044,
+      "eval_samples_per_second": 87.985,
+      "eval_steps_per_second": 10.998,
+      "step": 8000
     }
   ],
   "logging_steps": 1000,
@@ -159,7 +178,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6790124661368112.0,
+  "total_flos": 7765358762666736.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null