Training checkpoint - Epoch 1, Step 1

checkpoint-1/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8edc8b50305c869fd47454a532fa5d3b3bbb32df2bff27bfb83e450f72a27b7d
+oid sha256:8892bc567b0e9116bcc765cc048d7728a32aac015f02e1d320273d5ff23ff244
 size 14244

checkpoint-1/trainer_state.json

@@ -3,7 +3,7 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 1.0,
-  "eval_steps": 4000,
+  "eval_steps": 500,
   "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
@@ -15,6 +15,15 @@
       "learning_rate": 0.0,
       "loss": 2.4073,
       "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "eval_cosine_accuracy": 0.8333333134651184,
+      "eval_loss": 1.1724432706832886,
+      "eval_runtime": 2.8395,
+      "eval_samples_per_second": 2.113,
+      "eval_steps_per_second": 0.352,
+      "step": 1
     }
   ],
   "logging_steps": 4000,

checkpoint-1/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6951bb839d239af6b75461c6692130490816c65513ca3277e113a0116269ead9
+oid sha256:d15f3f8d8ef7d48fb84d1cbac4916e98a1684a23c018308e301ab1bed527a935
 size 5624

checkpoint-1/training_metrics.json

@@ -1,5 +1,12 @@
 {
-  "metrics_history": [],
+  "metrics_history": [
+    {
+      "epoch": 1.0,
+      "global_step": 1,
+      "eval_loss": 1.1724432706832886,
+      "eval_cosine_accuracy": 0.8333333134651184
+    }
+  ],
   "current_epoch": 1,
   "global_step": 1
 }