Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6d0fca814b1894e498d558db0303d247b6f5994869e45cfb5fd77f3efe4b3a9
+oid sha256:fac48492201a8c7e259286461cfce796fdef84a7fec1027f9d61c418c661a3f6
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b49407dd3b15afe1eddb0459d165999ed18c00225e9a2bacb15622ff7c00e37
+oid sha256:b0d4319bc80648570cad585bea17c7e16c7c83cabb9c7b87bfe906b3135cce14
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a03690f7e33a58df2b199d26809b29cf514d2b0503b304d54ac3aac06acbb30d
+oid sha256:d89ab08c606c453339e58bba31f2484472fcd10ea25125cb05c79b604e24909a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a4e7013bdf0cfef44b18348c4082377d680816016af2638e8995bf0bb3c8d9
+oid sha256:cf6a9a1e39c0655c6941309388d2a028b5b8dbbca031ca2500bdfcdc9f2c01aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6245287203371036,
+  "epoch": 0.6387225548902196,
   "eval_steps": 8,
-  "global_step": 88,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -306,6 +306,13 @@
       "eval_samples_per_second": 8.903,
       "eval_steps_per_second": 4.461,
       "step": 88
+    },
+    {
+      "epoch": 0.6387225548902196,
+      "grad_norm": 0.33444786071777344,
+      "learning_rate": 0.0,
+      "loss": 0.099,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -320,12 +327,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.341434837498593e+17,
+  "total_flos": 5.462661535975342e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null