Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:550d11d2e0d45d6a0d008261bef62de4360b487f887046f596e045ccd6f0a6eb
+oid sha256:dec94902aeef1da66fe3799f460774d7e11ff3ca1348ec1fd836a52e60e3a304
 size 69782384

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5388aad62ba3c6868bf12ad11bc022fae098f88cd35d07a7860da2b8bdeef209
+oid sha256:605837a2951e9cd7a6fa40ee23c3d5a25507180cd69e9506a92611de6b726860
 size 139790651

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc5c5eb75b44b8144a33c4463d137bd72be57e280cc3f9d5750a61e28416daac
+oid sha256:ff888a4ec4f2fab2bfd92e943e0a38d0b8f4e4883309963373b6809f52c08918
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4597266b92ceab6117e6a70e4971c3980afac249cc4bfe8f85b293a0771ae1e4
+oid sha256:f59f59a7859ef7b5a7545b424e0b16de3a0435ca89fcc924c7795332a2791a7e
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1800,
   "best_metric": 2.1885855197906494,
   "best_model_checkpoint": "./outputs/checkpoint-1800",
-  "epoch": 1.9543973941368078,
+  "epoch": 2.1715526601520088,
   "eval_steps": 200,
-  "global_step": 1800,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -332,6 +332,42 @@
       "eval_samples_per_second": 81.85,
       "eval_steps_per_second": 2.583,
       "step": 1800
+    },
+    {
+      "epoch": 2.008686210640608,
+      "grad_norm": 0.9358265399932861,
+      "learning_rate": 5.097252214851365e-05,
+      "loss": 2.165,
+      "step": 1850
+    },
+    {
+      "epoch": 2.0629750271444083,
+      "grad_norm": 1.0949631929397583,
+      "learning_rate": 4.601121531384579e-05,
+      "loss": 2.1348,
+      "step": 1900
+    },
+    {
+      "epoch": 2.1172638436482085,
+      "grad_norm": 1.3909953832626343,
+      "learning_rate": 4.1230843398675555e-05,
+      "loss": 2.1399,
+      "step": 1950
+    },
+    {
+      "epoch": 2.1715526601520088,
+      "grad_norm": 1.2448049783706665,
+      "learning_rate": 3.664742706752925e-05,
+      "loss": 2.1417,
+      "step": 2000
+    },
+    {
+      "epoch": 2.1715526601520088,
+      "eval_loss": 2.194857120513916,
+      "eval_runtime": 7.3786,
+      "eval_samples_per_second": 81.587,
+      "eval_steps_per_second": 2.575,
+      "step": 2000
     }
   ],
   "logging_steps": 50,
@@ -346,7 +382,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -360,7 +396,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.041672846318633e+17,
+  "total_flos": 5.602045311097897e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null