Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:925fc885d6b0dcfe27e6c1fd06764c67ae39ff3ea84df84c9283c25d2b2b074d
+oid sha256:5a9a933c3de11b9350f6512a280614cbbdcf8f9e6402a6040d42d95f8e70876b
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b7356f130e4143473353e2ee3afaecfdbac724d9987ce80443d4d1544c595a
+oid sha256:0ffc572c3908b39b89637c833f30cdede6580f52272d3812ef6eef8ea37680a8
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06e7ade66bdcd1ed7916d485fdbed1a0c8411b8e3e11bf2219b7f09cea2cf514
+oid sha256:e3f9f40d597a7abf41ad3ecf49e11bba5a13f6731550efb96e2fa2f1ae0dfe08
 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": 0.0015432098765432098,
+  "epoch": 0.0017146776406035665,
   "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": 44.044,
       "eval_steps_per_second": 22.022,
       "step": 9
+    },
+    {
+      "epoch": 0.0017146776406035665,
+      "grad_norm": 72.37802124023438,
+      "learning_rate": 0.0002,
+      "loss": 16.6177,
+      "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": 78955709202432.0,
+  "total_flos": 87728565780480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null