Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65637c669474ce6f1a0cf9957fdfa009afee0ed0480464f1c8ea33ddd027d6be
+oid sha256:302e7c35dca324756e4ea31dc057a2cb5bf2e09d7b9eee7b6e2e1610b0202550
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30efd9ae6df437d737658645cad5a90ae11ad2e16dcb8194f38c6fc3c154f0ea
+oid sha256:83340135f548e9405979b810a67afcd2e12b5be456bf000e10d7144a556dc0b3
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88471f2b3b1e4c205d9505ad6de006cb23590a0562a633e21bbcb4ef69f0d7ee
+oid sha256:19394caac0370dc5eb8bb3d271a9b6d245fc10d68ceffd549459fcf4f2e70bc9
 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": 0.0009324009324009324,
+  "epoch": 0.0013986013986013986,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 22.978,
       "eval_steps_per_second": 11.489,
       "step": 6
+    },
+    {
+      "epoch": 0.0010878010878010878,
+      "grad_norm": 2.7380995750427246,
+      "learning_rate": 0.00014,
+      "loss": 4.7198,
+      "step": 7
+    },
+    {
+      "epoch": 0.0012432012432012432,
+      "grad_norm": 3.2857611179351807,
+      "learning_rate": 0.00016,
+      "loss": 5.6143,
+      "step": 8
+    },
+    {
+      "epoch": 0.0013986013986013986,
+      "grad_norm": 3.5267786979675293,
+      "learning_rate": 0.00018,
+      "loss": 4.7434,
+      "step": 9
+    },
+    {
+      "epoch": 0.0013986013986013986,
+      "eval_loss": 5.1117706298828125,
+      "eval_runtime": 117.98,
+      "eval_samples_per_second": 22.97,
+      "eval_steps_per_second": 11.485,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1664607823331328.0,
+  "total_flos": 2450672628793344.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null