Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:360580d1ecd0e1a934f44c0b46e8ecbb14511c68d4adf11c01b33bdd8b9b5d05
+oid sha256:e0d17d32bab270c7203d31fde873b36f4b5fae85b4283c077edf12f1787eee59
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0e0d833cbadb29ef84f0e9d20f730ef89d18cc273c8e4eded87031ac74a38a0
+oid sha256:228d3196924ea62540817386ef023ad5ed96319da00ab8b0a6a17a9c42acf5e2
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b17726bf4924e2e3669e973dbbdd33c2cca6c199fefe136519cdc6a63dcd906
+oid sha256:60244c0428b1f7a9e3905a973f4f056138818fd34092c37d3c9603047a84b069
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00024897815216714733,
+  "epoch": 0.00027664239129683034,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 11.397,
       "eval_steps_per_second": 5.699,
       "step": 9
+    },
+    {
+      "epoch": 0.00027664239129683034,
+      "grad_norm": 3.7346112728118896,
+      "learning_rate": 0.0002,
+      "loss": 0.4842,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 501714738216960.0,
+  "total_flos": 550662517555200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null