Training in progress, step 55, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97a742c5c008a4bb04d731942ecfee4c1109062b5ee267fee7fee0f7a08054b1
+oid sha256:24669aafbde0781e2b51861144b52b6fc69159aa4f6da3d6591fafc60f5f5e0a
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb28265179b220a69fd9689dca9c54ae06e8a4dda428c017537402b1db4aa46e
+oid sha256:523d0bd348b172f252af377e1bb8ee264e0486947282767d9fbe6f6393279a85
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eee6eae3b8186ef126160899f88aa5d837d5e4baeb214aac70c66bbeb9a29a7
+oid sha256:f5502edcb21751d317e37d165e143beeff183b4a80ff928662c50848a9bbcc9a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79af33a7cc5e89926792af60c545e28f6f3569216a6e1a04e51a93b6477fd5cc
+oid sha256:59fb9c579d7f7f4aa986f5f762cd9981f0dcd26b5aa72ad6a0ef96ae89405fbd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.025225225225225224,
+  "epoch": 0.03303303303303303,
   "eval_steps": 14,
-  "global_step": 42,
+  "global_step": 55,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,13 @@
       "eval_samples_per_second": 30.489,
       "eval_steps_per_second": 15.266,
       "step": 42
+    },
+    {
+      "epoch": 0.03003003003003003,
+      "grad_norm": 1.8236432075500488,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.6399,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -81,12 +88,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6840746816569344.0,
+  "total_flos": 8958120831221760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null