Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9261e9afe6e2ac3ff3bc24d7acd6a9740b6a9b6dcb72284361ab208baa24ca33
+oid sha256:de736a267c35db52f11d9f6e095d31985bebbff0877d5b8eab970c18b7c032ab
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05997fea32f6d797649a89f934a1b13ee89d150eb4e2123a9af23c3cd6289e38
+oid sha256:06a869dd62362728749d978d7c5ae1df4fbf66dc225c664dc1b38496e6e9925f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aae7470879e8f19f69edc3c78eb50abc11361e598294cc4a8c50a856c8142969
+oid sha256:a74f0fa67ad2ea453853ea9c83fafb9413743a4d7deb09428e0f1e45b1df8364
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000430462388348818,
+  "epoch": 0.0006456935825232271,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,35 @@
       "eval_samples_per_second": 12.068,
       "eval_steps_per_second": 6.035,
       "step": 6
+    },
+    {
+      "epoch": 0.0005022061197402877,
+      "grad_norm": 4.613923072814941,
+      "learning_rate": 0.00014,
+      "loss": 2.1972,
+      "step": 7
+    },
+    {
+      "epoch": 0.0005739498511317573,
+      "grad_norm": 5.623652935028076,
+      "learning_rate": 0.00016,
+      "loss": 1.9682,
+      "step": 8
+    },
+    {
+      "epoch": 0.0006456935825232271,
+      "grad_norm": 5.242792129516602,
+      "learning_rate": 0.00018,
+      "loss": 1.7976,
+      "step": 9
+    },
+    {
+      "epoch": 0.0006456935825232271,
+      "eval_loss": 0.4103832244873047,
+      "eval_runtime": 420.6357,
+      "eval_samples_per_second": 13.953,
+      "eval_steps_per_second": 6.978,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -84,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2104131456073728.0,
+  "total_flos": 3156197184110592.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null