Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d1559d5c4ceadde2aa023f48dd93b8416f2f8aa0643389bcba68c12b992efa8
+oid sha256:67c8fe930490649ce5cc11a5fe193cfd48bc0b97b88299ffd6ad76afde0040b4
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f0c475760564744c662dab6ac098185417c8813fd6a2b68031142b7baf6f03e
+oid sha256:043ea3e469648caba58a57596dc37634719c22f8059e744b1a94bd1ae02825a6
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:961a595705c86d1e3825267783cc61e0ff8cf7fff9fd42c90081270529f9b97c
+oid sha256:8ce8dfd2d06984e08483a3aee4cbb4be06065cfb35a021428755194fc5c9a8b5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12921cac8baef4519674a5132945a5195f3291a8d5b5367c7d05afa86f16027a
+oid sha256:de31fecea0d88f3221e03053e0cf20c02baea118bf0e2b1c0433dcc126081364
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6877643727244785,
-  "best_model_checkpoint": "training_dir/checkpoint-4000",
-  "epoch": 0.4238635159478648,
+  "best_metric": 0.6979166210878224,
+  "best_model_checkpoint": "training_dir/checkpoint-5000",
+  "epoch": 0.5298293949348309,
   "eval_steps": 1000,
-  "global_step": 4000,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -83,6 +83,25 @@
       "eval_samples_per_second": 87.65,
       "eval_steps_per_second": 10.956,
       "step": 4000
+    },
+    {
+      "epoch": 0.5298293949348309,
+      "grad_norm": 7.548835754394531,
+      "learning_rate": 9.520613614573348e-06,
+      "loss": 0.5089,
+      "step": 5000
+    },
+    {
+      "epoch": 0.5298293949348309,
+      "eval_accuracy": 0.7084790209790209,
+      "eval_f1": 0.6979166210878224,
+      "eval_loss": 0.8279535174369812,
+      "eval_precision": 0.7081949635182484,
+      "eval_recall": 0.7084790209790209,
+      "eval_runtime": 25.9523,
+      "eval_samples_per_second": 88.162,
+      "eval_steps_per_second": 11.02,
+      "step": 5000
     }
   ],
   "logging_steps": 1000,
@@ -102,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3879664659350064.0,
+  "total_flos": 4845766626498096.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null