Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c9ea197136412c298320477da31493c1e303dea2aa199643ebe4628c1975b1c
+oid sha256:c1c64a2ff1113c3d02dd16c6a17bab2555408d049c7bbd5301d114d9b4743cb2
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13921336a7c3cf37284fa9824893b7e730bd24afd72e919fa4ee37e374778d3c
+oid sha256:c49e98dbf0c9a605805b0f9a7b893d2f0a176aad4ee2933d30d6103f7d8d7d61
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b6a6a011f28f85007de1213aaf2d9d99df9d84c0278f3612751bd8de1562285
+oid sha256:7ece6b3cf12ab3425c1775b1dafa9dd975d0c94122e55acd5be3596d4a99c259
 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": 0.025034770514603615,
+  "epoch": 0.027816411682892908,
   "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": 183.991,
       "eval_steps_per_second": 91.995,
       "step": 9
+    },
+    {
+      "epoch": 0.027816411682892908,
+      "grad_norm": 0.0041886246763169765,
+      "learning_rate": 0.0002,
+      "loss": 11.9275,
+      "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": 1979203584.0,
+  "total_flos": 2215526400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null