Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:919a81d88a354bed1a8a9f84da43223a6140ffbb55f4cca3736607e80b1ca4d9
+oid sha256:c6ae06d4c096a7881c3b3d72b6e118969a9bc583e8d3ebb67537b2791e27687f
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdb4317a40a9e583f4814625268950957d1c603b6a675bf5232b07fe42c39368
+oid sha256:68f5087e619495b80b75ea87b1206e4d9ce0f9b57016bc51c21068f164cd3f11
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27e83968c2d0fcbd9ce3decdbd850180096a3c3813ec3f1e2e7fbcdcb1b335e3
+oid sha256:487921a1acd258b82e58b9ec98a7bf8fbb6715ade97fa26c5f93634426742553
 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": 0.0026578073089701,
+  "epoch": 0.003986710963455149,
   "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": 36.891,
       "eval_steps_per_second": 18.465,
       "step": 6
+    },
+    {
+      "epoch": 0.0031007751937984496,
+      "grad_norm": 1.5461033582687378,
+      "learning_rate": 0.00014,
+      "loss": 6.9512,
+      "step": 7
+    },
+    {
+      "epoch": 0.0035437430786267998,
+      "grad_norm": 1.9836843013763428,
+      "learning_rate": 0.00016,
+      "loss": 6.8547,
+      "step": 8
+    },
+    {
+      "epoch": 0.003986710963455149,
+      "grad_norm": 2.3089280128479004,
+      "learning_rate": 0.00018,
+      "loss": 7.3323,
+      "step": 9
+    },
+    {
+      "epoch": 0.003986710963455149,
+      "eval_loss": 1.5851309299468994,
+      "eval_runtime": 25.7305,
+      "eval_samples_per_second": 36.96,
+      "eval_steps_per_second": 18.499,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 979486818435072.0,
+  "total_flos": 1469230227652608.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null