Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ede73d81607b7e86d4765e09be448e1c940ec8d7ac98eae53aeb4750f0f050b
+oid sha256:4e4966a7329d4b462aa103e2a1c5c9d956c1ca5d874264adfccce09cfb98eedf
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:999588af1af3f2a1e23f9358fdbecf0048412da4e3ec19abfb036f9c2284dfbf
+oid sha256:e9649d1cd6546ae71420a5f729429484f882aec73618ff7c94ab57c73ebb6e55
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12c9ec99072471891fe01b67c9debdbf3481e6da822949c5e90120e8950f206a
+oid sha256:a9fe601a3134d3c8c35dec249b894bf1731c41640749a2e794f0e2b5b0425d77
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cac062fdb4ce16fef436cb1657d9b0b90fb8b8ccc992aa1ae34641b4a22f79ee
+oid sha256:a1c1654640bb39861446cad5a11b2015812421c6a3c7bda32abed762ad21cb63
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.37635514577655893,
-  "best_model_checkpoint": "training_dir/checkpoint-125",
-  "epoch": 1.0,
+  "best_metric": 0.6361710372570955,
+  "best_model_checkpoint": "training_dir/checkpoint-250",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 125,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -26,6 +26,25 @@
       "eval_samples_per_second": 78.749,
       "eval_steps_per_second": 9.844,
       "step": 125
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.521803855895996,
+      "learning_rate": 5e-05,
+      "loss": 0.5748,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6407342657342657,
+      "eval_f1": 0.6361710372570955,
+      "eval_loss": 0.8366930484771729,
+      "eval_precision": 0.6428210794762689,
+      "eval_recall": 0.6407342657342657,
+      "eval_runtime": 29.8222,
+      "eval_samples_per_second": 76.721,
+      "eval_steps_per_second": 9.59,
+      "step": 250
     }
   ],
   "logging_steps": 500,
@@ -45,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 203879241576000.0,
+  "total_flos": 407758483152000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null