Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ceabc6dd1e2e8db18d983cd5e50c76b99c24d70a1f1beab60bf6caf91c52d88
+oid sha256:22a55eb1f4d5749b49cbbd75a67e61b967160aeecb830d55331fb2549b413b60
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cca5c8e10dd029a75a732d0b2885ee15bfd31fda10577f500188d2593d564e3
+oid sha256:7a33342de0b2f113ff29e4b31d3a274310ce2051af0cf9b5c66ef6d1a8d7e52b
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb91e2e45c651d389a1f4a7175eaa9b1cb7c3752127424640499fdf51987e759
+oid sha256:2cd40db2a30439bddcbee41ef58cd13a17ffe2dbf0b0a533f0b6bac4c3e0b859
 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": 0.0002952271608988027,
+  "epoch": 0.0003280301787764474,
   "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": 54.744,
       "eval_steps_per_second": 27.372,
       "step": 9
+    },
+    {
+      "epoch": 0.0003280301787764474,
+      "grad_norm": 18.56484603881836,
+      "learning_rate": 0.0002,
+      "loss": 13.3511,
+      "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": 587654391398400.0,
+  "total_flos": 652949323776000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null