Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a1385dee8820512366b5b88f60185c7058cea65d96897dce9e0f39961e9bb0
+oid sha256:61163dc781a673fabac495efc72da626b4d6f351b118b52da1285d5b9c464a29
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b4a2280848b47441777249e51bf0f3fe3c2f651273089e3cd5d34f4816f536d
+oid sha256:752877d0464ccab2b5e32c70eac4938bd2dc159ad03abc1eded382dadba97a6c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b16e571b5200a459b1d8d0f1e526ee8e68933e666abc123060b4e85c87c58aaf
+oid sha256:574c700717b33f47ad8a70b47083271e5db120d9e87ae1c83258d7702c5eeb81
 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": 0.01932367149758454,
+  "epoch": 0.028985507246376812,
   "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": 22.529,
       "eval_steps_per_second": 11.35,
       "step": 6
+    },
+    {
+      "epoch": 0.02254428341384863,
+      "grad_norm": 4.297223091125488,
+      "learning_rate": 0.00014,
+      "loss": 1.1112,
+      "step": 7
+    },
+    {
+      "epoch": 0.02576489533011272,
+      "grad_norm": 3.5222208499908447,
+      "learning_rate": 0.00016,
+      "loss": 0.6196,
+      "step": 8
+    },
+    {
+      "epoch": 0.028985507246376812,
+      "grad_norm": 4.136260509490967,
+      "learning_rate": 0.00018,
+      "loss": 0.878,
+      "step": 9
+    },
+    {
+      "epoch": 0.028985507246376812,
+      "eval_loss": 0.2005186229944229,
+      "eval_runtime": 5.8322,
+      "eval_samples_per_second": 22.462,
+      "eval_steps_per_second": 11.317,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1139235360866304.0,
+  "total_flos": 1752669785948160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null