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:bfd3d6d005432ba9897bdcb4c7043c3e487e8f40fdbe71621b867faec1d37edc
+oid sha256:051d06354a95b5f086876cf3085c322009f7999a7cfde85af6863ce0fc7e8156
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0214d7c3b8a1f401987557a64dd876b1a37cd3bd6786591e5e7c1a95d24b20d
+oid sha256:7dcc5f80dcfb25f3ba280d300edfbd2f453f7600484f2d9121d37b99c5ee5cd4
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:930ecffcf53b9b309da4cbacd3e32aa53eac7f2224a5a4cb32ac9d960a3c629f
+oid sha256:85763b024e6d6bef80cd8a058173579d91097a76e4faf1b6d33bb0ba757ab567
 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": 0.022871664548919948,
+  "epoch": 0.025412960609911054,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 39.944,
       "eval_steps_per_second": 19.972,
       "step": 9
+    },
+    {
+      "epoch": 0.025412960609911054,
+      "grad_norm": 0.45385488867759705,
+      "learning_rate": 0.0002,
+      "loss": 5.3359,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 651326304288768.0,
+  "total_flos": 719886967898112.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null