Training in progress, epoch 1, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e99540a0b01d9e122429232d3db2bfea6c67b2a2b0c0bd486a56b037fee9e2b
+oid sha256:ecf462417a92064cf4abe16aa4acaa995fcc3e1e43d5ccc8262cc01de4c3a4d8
 size 36220072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c1fd80de48e068459f8c64e1d8a0a8258b2521026c5b23a519fe2199d15095d
+oid sha256:551e989d8402dffbcfa8cf3b23f8f74268b4d0f6a759404a4d3350d6f4b88279
 size 18763860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16cda6ccb039037336239ee1c2664a24ac6dc79bcc71492044533c2fca34891b
+oid sha256:fd53bba9ab96bbcb86335292936463ef3bf6e250d44e68a4c73325173bffab76
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcaddd05bf6c1cc5c89613f4644cc7156537682423f41251dfef48c1f9bc4e4b
+oid sha256:052060fe3af782f770f65363e67ed8fd0dc48c58828bf0a900327384e656ecc2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9939879759519038,
+  "epoch": 1.006012024048096,
   "eval_steps": 32,
-  "global_step": 124,
+  "global_step": 125,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -207,6 +207,13 @@
       "learning_rate": 6.819348298638839e-07,
       "loss": 1.2177,
       "step": 120
+    },
+    {
+      "epoch": 1.006012024048096,
+      "grad_norm": 0.7495393753051758,
+      "learning_rate": 0.0,
+      "loss": 1.4924,
+      "step": 125
     }
   ],
   "logging_steps": 5,
@@ -221,12 +228,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9892076627951616.0,
+  "total_flos": 9951787352064000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null