Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e217e3f0d1eb51ddc08be9650572e04135f6e2d2555f937f82c312adbbd0fe7
+oid sha256:0d794fe9cc6e412dcd0eeedb33991c8449793a1a8fbc46f90872188a0a8569a6
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f38da5f2a39acb1eea6b0fd1b37b5c5b5fcd7faeda47fb6f5923996248eb1c
+oid sha256:2bc3b02bf7e0080716b643d4a610e82f7189ce513f5d8b4bd50658d2078e0b0e
 size 7086458

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f98bc0c3a7e4ea6a8ac7c366cccb4bb7940a8ee426517e92269de9f27e81c9a
+oid sha256:4ce6a303290374d7519e933c120f942e73d4d87c9a659cb0dc0b3be5a34515a6
 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": 9.91970549496575e-05,
+  "epoch": 0.00011021894994406389,
   "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": 34.538,
       "eval_steps_per_second": 17.269,
       "step": 9
+    },
+    {
+      "epoch": 0.00011021894994406389,
+      "grad_norm": 0.7852161526679993,
+      "learning_rate": 0.0002,
+      "loss": 2.9233,
+      "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": 249907654950912.0,
+  "total_flos": 277675172167680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null