Training in progress, step 5500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:685d53982b27eb365dec7e10b5430fca13c6e0fa7574169dc00b5b61713d4d8e
+oid sha256:27b44157417e39f37d53f97660159534caa17c9e92cc0fcc65d26cdc58df41c2
 size 498686648

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e480ea2c1707535961a915ad7d0c076244f7d677a129489077a8242a2b9126a7
+oid sha256:d0a598fbe7a9896408099f5b9156dc689745bd20c4fc91ba85bea8bdd2ed788e
 size 997493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e46df96471f815a1d294c24fe73c8ab67a0d41f321e80dcd299bde46010e94cf
+oid sha256:c44ae4ad313b4be83c6fe4120f4de7b8df0b41f03db919b420b2e256111040f7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e4b999bc7117f5e365eaf55ab190141de7aaca3ce426abdc3f6d80268e7bf79
+oid sha256:1756636f56007ccf3026f60661401a9b281d6ff9e2176d95116df6815604e882
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.46239224076271057,
-  "best_model_checkpoint": "results/checkpoint-4500",
-  "epoch": 0.474068455484972,
+  "best_metric": 0.45522668957710266,
+  "best_model_checkpoint": "results/checkpoint-5500",
+  "epoch": 0.5214753010334693,
   "eval_steps": 500,
-  "global_step": 5000,
+  "global_step": 5500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -207,6 +207,26 @@
       "eval_samples_per_second": 59.804,
       "eval_steps_per_second": 0.469,
       "step": 5000
+    },
+    {
+      "epoch": 0.5214753010334693,
+      "grad_norm": 426242.5,
+      "learning_rate": 1.9140987958661234e-05,
+      "loss": 0.5104,
+      "step": 5500
+    },
+    {
+      "epoch": 0.5214753010334693,
+      "eval_accuracy": 0.868323910097659,
+      "eval_f1_macro": 0.8363938907947726,
+      "eval_f1_w": 0.8695247067175498,
+      "eval_loss": 0.45522668957710266,
+      "eval_precision": 0.8726509048119306,
+      "eval_recall": 0.868323910097659,
+      "eval_runtime": 357.8353,
+      "eval_samples_per_second": 59.807,
+      "eval_steps_per_second": 0.469,
+      "step": 5500
     }
   ],
   "logging_steps": 500,
@@ -226,7 +246,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.421368070144e+16,
+  "total_flos": 9.2635048771584e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null