Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10f7ff7105e426db44677363ec257ea6367728453648fe69a2f39908eb01b309
+oid sha256:4d2f877d46101917c8994c5626a62d2794eb99fa6c13018a8fb9ac5d6e197681
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa0478d3c099b50d76d4345f37bd1ca5166a8af132519b453c7e47d39f1c2982
+oid sha256:4a20dca287e514467c69aef4bc21cf39ff5aafb12e109e0b8439d665faaea13c
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1154dfe42fb478d85e8d143f5afbea6d197888318a52d73aab7cec92cc59b74
+oid sha256:adf96cbd7ccb91b3705ba75b10d94b4cee9c0c6989e92c5bbd9979d0bc076e1b
 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": 0.004740776758038048,
+  "epoch": 0.0060779189205616,
   "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": 3.076,
       "step": 35
+    },
+    {
+      "epoch": 0.00486233513644928,
+      "grad_norm": 1.3508284091949463,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.0583,
+      "step": 40
+    },
+    {
+      "epoch": 0.00486233513644928,
+      "eval_loss": 2.9765591621398926,
+      "eval_runtime": 101.1821,
+      "eval_samples_per_second": 34.235,
+      "eval_steps_per_second": 17.118,
+      "step": 40
+    },
+    {
+      "epoch": 0.005470127028505439,
+      "grad_norm": 0.9980248808860779,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.9624,
+      "step": 45
+    },
+    {
+      "epoch": 0.0060779189205616,
+      "grad_norm": 1.4837217330932617,
+      "learning_rate": 0.0,
+      "loss": 2.9839,
+      "step": 50
+    },
+    {
+      "epoch": 0.0060779189205616,
+      "eval_loss": 2.9737050533294678,
+      "eval_runtime": 100.8358,
+      "eval_samples_per_second": 34.353,
+      "eval_steps_per_second": 17.176,
+      "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": 1070427543699456.0,
+  "total_flos": 1353068524339200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null