Training in progress, epoch 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:377015a2f2d0a1d535fd0614cb6e75174ab1a81ff78e3fadd2e4923bce2c9638
+oid sha256:a6f13d3f381449f8d84b7ca05fb821a8b2c0861629beaa791e6c2b5fc00bbb5d
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:502a84f2960672887c9f9567e71498adf67f718978d01edd09c4a50418162bd8
+oid sha256:9765040586104af3a74cdbea9cc7074b0e48ef0d1226c3c15c17be1de83b9f59
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e6f92a8b13bcc897bf3bb961d25b22aa9f5e3b3c3e1dda5ed2738319d087e7d
+oid sha256:675b9a4f8cd0e254dcba3b5459763afcac5d970080440d891cee0ad59e24dfb1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee86abee0989df8e1c5461d5ecfc6d42b43c8879a30063d7c1ee114f0c589f6
+oid sha256:74a0adf096c9eebfe9a2fa6c4d4fa6dd5ed912c3085653d4e028c18b90b90dc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6361710372570955,
   "best_model_checkpoint": "training_dir/checkpoint-250",
-  "epoch": 4.0,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 625,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -83,6 +83,25 @@
       "eval_samples_per_second": 76.538,
       "eval_steps_per_second": 9.567,
       "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 7.975765705108643,
+      "learning_rate": 5e-05,
+      "loss": 0.2239,
+      "step": 625
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6324300699300699,
+      "eval_f1": 0.6186338450685905,
+      "eval_loss": 1.4131898880004883,
+      "eval_precision": 0.657121853967928,
+      "eval_recall": 0.6324300699300699,
+      "eval_runtime": 29.8857,
+      "eval_samples_per_second": 76.558,
+      "eval_steps_per_second": 9.57,
+      "step": 625
     }
   ],
   "logging_steps": 500,
@@ -102,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 815516966304000.0,
+  "total_flos": 1019396207880000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null