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:a3e8edaacc9b3bd69978f74ae5b8e0d8de266712961390ac85111de732a482b2
+oid sha256:45cb56058752b456aed83662721ca547ea0b9faf20a4eeb56a4c129f7130f709
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baa73e772544464ccf8f2436f87470eb4ffed2e88291935d4fe9f08514e27731
+oid sha256:e675e65d9a6237017e47cac5abe5ecd2ac2133f7184094a8ece83a7b82038b20
 size 263088

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
+oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
 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": 0.010084033613445379,
+  "epoch": 0.015126050420168067,
   "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": 110.122,
       "eval_steps_per_second": 55.28,
       "step": 6
+    },
+    {
+      "epoch": 0.011764705882352941,
+      "grad_norm": 10.299397468566895,
+      "learning_rate": 0.00014,
+      "loss": 44.2292,
+      "step": 7
+    },
+    {
+      "epoch": 0.013445378151260505,
+      "grad_norm": 9.66534423828125,
+      "learning_rate": 0.00016,
+      "loss": 44.3521,
+      "step": 8
+    },
+    {
+      "epoch": 0.015126050420168067,
+      "grad_norm": 10.421772956848145,
+      "learning_rate": 0.00018,
+      "loss": 44.1104,
+      "step": 9
+    },
+    {
+      "epoch": 0.015126050420168067,
+      "eval_loss": 10.953063011169434,
+      "eval_runtime": 2.2588,
+      "eval_samples_per_second": 111.119,
+      "eval_steps_per_second": 55.781,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 499189284864.0,
+  "total_flos": 748783927296.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null