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:f8d2995af1cc5890c52eddca0f14641f7c832f0ba7d22c34522b9f96a3e89400
+oid sha256:709fcf352a889f6f8d50febda61767450c6102f0bd7c2547fb1b96b9f246c0b4
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1124b3d2729c4eb923a26f82155a43320c9775a5c3b7073ad8a662f2af0b402e
+oid sha256:6acf88d32a57280630051294c727302d8f44982bb5529f7183c46d946419b142
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0c1b87f8654c8017ee20bafb0743e5a5c10d15bcd99fdd912d066afaa342d7d
+oid sha256:a52de475c9ee7fccf32a03e0dd53231b1635475fc4aa087879ca1708e4c7b973
 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": 0.00599250936329588,
+  "epoch": 0.008988764044943821,
   "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": 17.476,
       "eval_steps_per_second": 8.738,
       "step": 6
+    },
+    {
+      "epoch": 0.006991260923845194,
+      "grad_norm": 0.32162007689476013,
+      "learning_rate": 0.00014,
+      "loss": 0.9614,
+      "step": 7
+    },
+    {
+      "epoch": 0.007990012484394507,
+      "grad_norm": 0.3540832996368408,
+      "learning_rate": 0.00016,
+      "loss": 0.9271,
+      "step": 8
+    },
+    {
+      "epoch": 0.008988764044943821,
+      "grad_norm": 0.5317844152450562,
+      "learning_rate": 0.00018,
+      "loss": 0.9986,
+      "step": 9
+    },
+    {
+      "epoch": 0.008988764044943821,
+      "eval_loss": 0.943752646446228,
+      "eval_runtime": 21.8784,
+      "eval_samples_per_second": 19.288,
+      "eval_steps_per_second": 9.644,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -84,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 492029198991360.0,
+  "total_flos": 738043798487040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null