Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:300030c64a040eebdce7f56bfbb07229963377af5de43cf442518036da1e52ff
+oid sha256:d04aa13938cf3a0001c02251be761883011bc3572a9f990a2ba31fc50c694769
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abd397d678e4bb5cbc2e8ffd54ce508b0c82866e5a3709438b6b0abb48d037b2
+oid sha256:e28bfbfe05f8bb6f81679b0905629654b780070f5d327cb954418f4bce975677
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfbb4cc74a9123e469cd1f379297969ebdc6fd5c7772857ffca5080eff9696a3
+oid sha256:ee1cb0c2c361df7742214ffd8d8863c4a6e48a63e8777f02dc03184c3862b111
 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": 0.00015950588621027308,
+  "epoch": 0.00017722876245585895,
   "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": 19.056,
       "eval_steps_per_second": 9.528,
       "step": 9
+    },
+    {
+      "epoch": 0.00017722876245585895,
+      "grad_norm": 1.0697853565216064,
+      "learning_rate": 0.0002,
+      "loss": 1.1478,
+      "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": 1606627350282240.0,
+  "total_flos": 1771409642618880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null