Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cfc392ad59ec41a717c63b3884a52ad51126af28bbcd243422dd295cfbfd94b
+oid sha256:956ba5725689dabbefdf65752724daaab2885f4cc056b9141a7fdccaa61f6647
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12001a141ccdaf36d5f66675c4e096c5adfc4a496e93a2a897d1e57621e69acb
+oid sha256:650849a0970f1d8033080bc52c2e5210b3d28ea1e880c2eb3edeb53009090125
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2241e47e90dbe5d89c54cba6f32860dcccf65414196b69f5497673057084cc8
+oid sha256:2291447074fbfec72a703a90e1ba8ffca89c3604099f8cd2c5c4519e2f94b932
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0148204446133384,
+  "epoch": 0.019000570017100513,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 44.3179,
       "step": 35
+    },
+    {
+      "epoch": 0.01520045601368041,
+      "grad_norm": 1.4363198280334473,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 44.2515,
+      "step": 40
+    },
+    {
+      "epoch": 0.01520045601368041,
+      "eval_loss": 11.059069633483887,
+      "eval_runtime": 5.3118,
+      "eval_samples_per_second": 208.592,
+      "eval_steps_per_second": 104.296,
+      "step": 40
+    },
+    {
+      "epoch": 0.01710051301539046,
+      "grad_norm": 1.5815496444702148,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 44.2005,
+      "step": 45
+    },
+    {
+      "epoch": 0.019000570017100513,
+      "grad_norm": 1.4893732070922852,
+      "learning_rate": 0.0,
+      "loss": 44.2665,
+      "step": 50
+    },
+    {
+      "epoch": 0.019000570017100513,
+      "eval_loss": 11.057279586791992,
+      "eval_runtime": 5.1829,
+      "eval_samples_per_second": 213.781,
+      "eval_steps_per_second": 106.891,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 380969680896.0,
+  "total_flos": 487062503424.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null