Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37154ccd2d8ecf31a38c5b280abf07588faaf8be112324982068d7128c55649d
+oid sha256:ef92e0fcc9111ec7a6d03ed5db4a005ae8f1f95e53caa5fb92577828306c4795
 size 313820248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8342ad048df0e0273ef265fe27b31f5078b6492fc0b3869c719757fb097a44d2
+oid sha256:1a1b34829f9576cb75550614651d2d6e6811bef3584df719870d4bb4075f213d
 size 159641092

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a85f2cd6074e6b196ce3e21a5e046f42204dac923aae3837de01229908be834
+oid sha256:7d9f31a121da7da940bff27264206c17c5b0de92506f9ffbacadc7ea6f55f96a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005157297576070139,
+  "epoch": 0.006876396768093519,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 28.496,
       "eval_steps_per_second": 3.566,
       "step": 15
+    },
+    {
+      "epoch": 0.006188757091284167,
+      "grad_norm": 2.5343384742736816,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.6198,
+      "step": 18
+    },
+    {
+      "epoch": 0.006876396768093519,
+      "eval_loss": 0.6454147100448608,
+      "eval_runtime": 171.8957,
+      "eval_samples_per_second": 28.5,
+      "eval_steps_per_second": 3.566,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6076163382312960.0,
+  "total_flos": 8101551176417280.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null