Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d3408bd268b2e55ce9e2680ca933d0e18463d019576dc820b0d9ca29728da6f
+oid sha256:0f7ec55d0d67152854ebe7902e368f300849fec538a8f021e2f7fd19c849a17f
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:388c262919a333d62a0a0c0b49adb0d46206ca5c81da784b3fa65a9c772e543c
+oid sha256:dbe70b6dff690678e2ebe12b45bd002e54cbccf629c844c816f1ed09daf3f010
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:578d7a57542da19ac1783f882a9b0423edb00199253164abf5fb151eb7176f96
+oid sha256:b543366cfabdd66b7ed63582e5303f4bff99a84636648762ece313be1d5466ed
 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

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0031529164477141357,
+  "epoch": 0.004729374671571204,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,35 @@
       "eval_samples_per_second": 39.451,
       "eval_steps_per_second": 19.725,
       "step": 6
+    },
+    {
+      "epoch": 0.0036784025223331584,
+      "grad_norm": 0.4450327455997467,
+      "learning_rate": 0.00012,
+      "loss": 0.1192,
+      "step": 7
+    },
+    {
+      "epoch": 0.004203888596952181,
+      "grad_norm": 0.39254745841026306,
+      "learning_rate": 0.00014,
+      "loss": 0.0797,
+      "step": 8
+    },
+    {
+      "epoch": 0.004729374671571204,
+      "grad_norm": 0.3380250632762909,
+      "learning_rate": 0.00016,
+      "loss": 0.0549,
+      "step": 9
+    },
+    {
+      "epoch": 0.004729374671571204,
+      "eval_loss": 0.03407502919435501,
+      "eval_runtime": 20.178,
+      "eval_samples_per_second": 39.746,
+      "eval_steps_per_second": 19.873,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -93,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 194578955108352.0,
+  "total_flos": 291868432662528.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null