Training in progress, step 51, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92a5195cc750844b0bbc895066277d57c0718916d29688804e359cf73cc5ce6f
+oid sha256:68e3c611d6ce76d2866d44bad53b9c51229d108c9b1241a912c3c9a852091da3
 size 2964338224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b70c7fb24e252910d76b9e2aec21c3fc8339de03d6b82df521ec794192bf984b
+oid sha256:b7be84f71128c614b6a55c6d6b3eb6e435a14f8fdeac24ea4e85269dc51bec0b
 size 1485440604

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:535489482a0b34fccaa30a29409920995d6879a3a5e9c37a34bb64e915525f48
+oid sha256:a0f1e84e375ad3e6c086ea2862ff0f2ffe96eaee10ac448e38d6d541f8b61804
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7576301615798924,
+  "epoch": 2.9299820466786355,
   "eval_steps": 500,
-  "global_step": 48,
+  "global_step": 51,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -343,6 +343,27 @@
       "learning_rate": 6.576144030555259e-07,
       "loss": 1.9854,
       "step": 48
+    },
+    {
+      "epoch": 2.81508078994614,
+      "grad_norm": 1.2900848388671875,
+      "learning_rate": 2.9298940549128964e-07,
+      "loss": 1.9512,
+      "step": 49
+    },
+    {
+      "epoch": 2.872531418312388,
+      "grad_norm": 1.1324858665466309,
+      "learning_rate": 7.335497040648898e-08,
+      "loss": 1.9581,
+      "step": 50
+    },
+    {
+      "epoch": 2.9299820466786355,
+      "grad_norm": 1.2011033296585083,
+      "learning_rate": 0.0,
+      "loss": 1.9738,
+      "step": 51
     }
   ],
   "logging_steps": 1,
@@ -357,12 +378,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.3055149893382144e+16,
+  "total_flos": 3.49530087730176e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null