Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802f3710954909baac3df55a618d0a37c7528f25b8f194774ea780454be955d8
+oid sha256:dd65dcd692e27447c194549e54c14a3c22566ada7b7f18d5900f9c53a9d22790
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81141cb80dcc2e571d0c0bdc1f34a5fbd243bd68913614c768cfdf2acbd2b2c7
+oid sha256:d967ca6dace53d61e75561d156ec781ec8a9197125e10a3001ec3cc5c10701b1
 size 1342555602

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68529ee711356fd9d47647e5bd3dd9d92d8d90801ebf2381a18d532f68111077
+oid sha256:3bf26d2680b85dcd667f80e96b5cc6e90865b5e4d06d5ef11eb1400f3de4c7b7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7041fa0be7432c15ac468c1425bc3b5d595e4b5b769cfa7728743ab80ef12291
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3504424778761062,
+  "epoch": 0.35398230088495575,
   "eval_steps": 9,
-  "global_step": 99,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -236,6 +236,13 @@
       "eval_samples_per_second": 19.317,
       "eval_steps_per_second": 2.424,
       "step": 99
+    },
+    {
+      "epoch": 0.35398230088495575,
+      "grad_norm": 0.4104834496974945,
+      "learning_rate": 0.0,
+      "loss": 0.6769,
+      "step": 100
     }
   ],
   "logging_steps": 5,
@@ -250,12 +257,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.4934284429583974e+17,
+  "total_flos": 1.508513578745856e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null