Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:660e259502605e834dd8abbd515a95cf791c90b835cd8619af34ae2871638746
+oid sha256:03c7d180a19b44794ca000d2ac9a044f1208efd45d788b186b2cb4aa92a38f39
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f893ac69d7d1f10d39868874c3b9562ac71e9c3dd7da29564ebf79fb717f4bb0
+oid sha256:557ea13c11ce98813552511fa97e10d4f01136341ec47a731712dc2928949737
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:049ef9d402621f8d67191fa7981b9705ec1748fcb4431765ca3a28fee3882315
+oid sha256:b70f29a81cab5749b7acb47c2046572b3022dd01b41109c8e1baa88cfd573b4b
 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": 0.0003794946396382151,
+  "epoch": 0.0005692419594573227,
   "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": 29.416,
       "eval_steps_per_second": 14.708,
       "step": 6
+    },
+    {
+      "epoch": 0.0004427437462445843,
+      "grad_norm": 13.617958068847656,
+      "learning_rate": 0.00014,
+      "loss": 7.4227,
+      "step": 7
+    },
+    {
+      "epoch": 0.0005059928528509535,
+      "grad_norm": 12.062705993652344,
+      "learning_rate": 0.00016,
+      "loss": 6.9968,
+      "step": 8
+    },
+    {
+      "epoch": 0.0005692419594573227,
+      "grad_norm": 14.231619834899902,
+      "learning_rate": 0.00018,
+      "loss": 5.896,
+      "step": 9
+    },
+    {
+      "epoch": 0.0005692419594573227,
+      "eval_loss": 6.201642990112305,
+      "eval_runtime": 226.526,
+      "eval_samples_per_second": 29.392,
+      "eval_steps_per_second": 14.696,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1146654849761280.0,
+  "total_flos": 1719982274641920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null