Training in progress, step 2400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a227244b79f305f140948c1079fcdc545f071391bb7e4ff9cf542a898d157d1c
+oid sha256:e881eea67951f715a0412c658550fa6656f80eb9c2e7babf1715b545a2d6c453
 size 69782384

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9e0d7d55f9a230dad78340581c7686c5db109d5d23cb37fd0af07013b1770c4
+oid sha256:6d4dbaa4a93c925e7206f796b1b5cb1d4f8097fcd0cada8da8eca9fa94e98a40
 size 139790651

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92bebe68c4903b16edae13a87b639062f86297d20f12bfc3a43205a7d64356a6
+oid sha256:a29859d5dfe7ec5553a7575bdf1fff1111c940a25116f4b3204c18d1ea7bcdb7
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42a9c19735c8da4979dd9d9844a70622260a91c03b4b752eeed5aefa51d6bbfb
+oid sha256:9ebdfd2092dbf93cc1de964feb5cc7ccb4c109e2c86de6e8d8008013b0ca48f9
 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": 2.3887079261672097,
+  "epoch": 2.6058631921824107,
   "eval_steps": 200,
-  "global_step": 2200,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -404,6 +404,42 @@
       "eval_samples_per_second": 81.956,
       "eval_steps_per_second": 2.587,
       "step": 2200
+    },
+    {
+      "epoch": 2.44299674267101,
+      "grad_norm": 1.4523568153381348,
+      "learning_rate": 1.7196383108428315e-05,
+      "loss": 2.1359,
+      "step": 2250
+    },
+    {
+      "epoch": 2.49728555917481,
+      "grad_norm": 1.3263523578643799,
+      "learning_rate": 1.4090705132619631e-05,
+      "loss": 2.1206,
+      "step": 2300
+    },
+    {
+      "epoch": 2.5515743756786105,
+      "grad_norm": 1.4148005247116089,
+      "learning_rate": 1.1272938645118803e-05,
+      "loss": 2.1314,
+      "step": 2350
+    },
+    {
+      "epoch": 2.6058631921824107,
+      "grad_norm": 1.9476280212402344,
+      "learning_rate": 8.752526947077045e-06,
+      "loss": 2.1254,
+      "step": 2400
+    },
+    {
+      "epoch": 2.6058631921824107,
+      "eval_loss": 2.189617395401001,
+      "eval_runtime": 7.3524,
+      "eval_samples_per_second": 81.878,
+      "eval_steps_per_second": 2.584,
+      "step": 2400
     }
   ],
   "logging_steps": 50,
@@ -418,7 +454,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -427,12 +463,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.162730083190702e+17,
+  "total_flos": 6.723721683521372e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null