Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36ce22a14aa74361686e1f20fa99ce35048ca19ea540d78da3a55647395afa1a
+oid sha256:20b84da71b21580e0e837c45e154d1f3eb8fe9597a16529a733fcb56aa18fd73
 size 2185308216

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc0d4f9af17af8824f8626a2c5724a74520a240a595afc67fc918cd27fccfc42
+oid sha256:af8639a119f291f4e058202deb999637e5898f0e8a43a8bb25073db145705e56
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2fe91e4b71ad96971401f0069a1c0bd726c6e3d3f180c7c5724b4adc2dcccdc
+oid sha256:7170a2d9b24ecc77552af509fa5ca848d0a66f21c29b073517cc02fd19368fe3
 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": 0.056074766355140186,
+  "epoch": 0.08411214953271028,
   "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": 13.792,
       "eval_steps_per_second": 7.049,
       "step": 6
+    },
+    {
+      "epoch": 0.06542056074766354,
+      "grad_norm": 6.730138301849365,
+      "learning_rate": 0.00014,
+      "loss": 2.4926,
+      "step": 7
+    },
+    {
+      "epoch": 0.07476635514018691,
+      "grad_norm": 5.640018939971924,
+      "learning_rate": 0.00016,
+      "loss": 1.8213,
+      "step": 8
+    },
+    {
+      "epoch": 0.08411214953271028,
+      "grad_norm": 6.035444259643555,
+      "learning_rate": 0.00018,
+      "loss": 1.2622,
+      "step": 9
+    },
+    {
+      "epoch": 0.08411214953271028,
+      "eval_loss": 0.6004507541656494,
+      "eval_runtime": 3.3196,
+      "eval_samples_per_second": 13.556,
+      "eval_steps_per_second": 6.929,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1109739152867328.0,
+  "total_flos": 1664608729300992.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null