Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:788d6c431bc3a767c745905b4e7ed555f8414be5ad33a75e048c2a99e3480105
+oid sha256:21800ac455b61d9a291348819a9f506241ed15cb9ce42fcae5c6852a38d8eb20
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8224398a35326ca85824385ac38b716ad595cceedf9e8fdc2a14af90136f1230
+oid sha256:bd602d490090a63d693a8bad9a7c619495a141c87190a1645ac6eb5b15cf7280
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:332d05b227720963e561614b208f5e39d94130cc5b67b712d8aec704897dc6e6
+oid sha256:4d6b6662714e5b994bba16e514b50ddc831eee9d5bb5c1d43535e2d3b4f207d3
 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": 0.03293687099725526,
+  "epoch": 0.036596523330283626,
   "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": 14.15,
       "eval_steps_per_second": 7.136,
       "step": 9
+    },
+    {
+      "epoch": 0.036596523330283626,
+      "grad_norm": 2.800792694091797,
+      "learning_rate": 0.0002,
+      "loss": 0.6246,
+      "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": 1483040631029760.0,
+  "total_flos": 1647822923366400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null