Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44bd8da97b3f61c2e5a4e0d260813d628a0c80bbb91b26e4b86d42e6455d8f18
+oid sha256:75e08192ab5638b9ce42e59b077f8b6e526f370d825b224ca5bb43f0f1e59f55
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff58585b44e57a4f9a5b7b0c9cca6ae4abd340ad166fa62290f43e80ce65c38d
+oid sha256:8b97f26ffecfe1c09db04f70d1f6a88809ee7772980e0cdc2a024951bb425596
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f53162aa47c174011d89c771d2dd00617d859ffee2a21ef2744c9bd851968327
+oid sha256:66d089a5ddfd345bf1a17d8d5450b0bcd10b1aeb4a8683ba1633f2f30f445d12
 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": 0.7123287671232876,
+  "epoch": 0.91324200913242,
   "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": 10.8498,
       "step": 35
+    },
+    {
+      "epoch": 0.730593607305936,
+      "grad_norm": 5.057796955108643,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.128,
+      "step": 40
+    },
+    {
+      "epoch": 0.730593607305936,
+      "eval_loss": 2.6654646396636963,
+      "eval_runtime": 0.697,
+      "eval_samples_per_second": 32.999,
+      "eval_steps_per_second": 17.217,
+      "step": 40
+    },
+    {
+      "epoch": 0.821917808219178,
+      "grad_norm": 5.423208713531494,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.6538,
+      "step": 45
+    },
+    {
+      "epoch": 0.91324200913242,
+      "grad_norm": 5.391549110412598,
+      "learning_rate": 0.0,
+      "loss": 10.6193,
+      "step": 50
+    },
+    {
+      "epoch": 0.91324200913242,
+      "eval_loss": 2.663372278213501,
+      "eval_runtime": 0.6812,
+      "eval_samples_per_second": 33.762,
+      "eval_steps_per_second": 17.615,
+      "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": 1224146713313280.0,
+  "total_flos": 1582433556234240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null