Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dec94902aeef1da66fe3799f460774d7e11ff3ca1348ec1fd836a52e60e3a304
+oid sha256:a227244b79f305f140948c1079fcdc545f071391bb7e4ff9cf542a898d157d1c
 size 69782384

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:605837a2951e9cd7a6fa40ee23c3d5a25507180cd69e9506a92611de6b726860
+oid sha256:f9e0d7d55f9a230dad78340581c7686c5db109d5d23cb37fd0af07013b1770c4
 size 139790651

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff888a4ec4f2fab2bfd92e943e0a38d0b8f4e4883309963373b6809f52c08918
+oid sha256:92bebe68c4903b16edae13a87b639062f86297d20f12bfc3a43205a7d64356a6
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f59f59a7859ef7b5a7545b424e0b16de3a0435ca89fcc924c7795332a2791a7e
+oid sha256:42a9c19735c8da4979dd9d9844a70622260a91c03b4b752eeed5aefa51d6bbfb
 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": 2.1715526601520088,
+  "epoch": 2.3887079261672097,
   "eval_steps": 200,
-  "global_step": 2000,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -368,6 +368,42 @@
       "eval_samples_per_second": 81.587,
       "eval_steps_per_second": 2.575,
       "step": 2000
+    },
+    {
+      "epoch": 2.225841476655809,
+      "grad_norm": 1.2955018281936646,
+      "learning_rate": 3.227632691927414e-05,
+      "loss": 2.1308,
+      "step": 2050
+    },
+    {
+      "epoch": 2.2801302931596092,
+      "grad_norm": 1.0340995788574219,
+      "learning_rate": 2.8132192008487768e-05,
+      "loss": 2.129,
+      "step": 2100
+    },
+    {
+      "epoch": 2.3344191096634095,
+      "grad_norm": 1.2585651874542236,
+      "learning_rate": 2.4228910751455625e-05,
+      "loss": 2.1403,
+      "step": 2150
+    },
+    {
+      "epoch": 2.3887079261672097,
+      "grad_norm": 1.2523435354232788,
+      "learning_rate": 2.0579564381328775e-05,
+      "loss": 2.1197,
+      "step": 2200
+    },
+    {
+      "epoch": 2.3887079261672097,
+      "eval_loss": 2.190831422805786,
+      "eval_runtime": 7.3454,
+      "eval_samples_per_second": 81.956,
+      "eval_steps_per_second": 2.587,
+      "step": 2200
     }
   ],
   "logging_steps": 50,
@@ -382,7 +418,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -396,7 +432,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.602045311097897e+17,
+  "total_flos": 6.162730083190702e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null