Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44904ecf8a5e9066eb92b9ca2186ce66796c37ed2d4bb7a4ac4a00f8039c575b
+oid sha256:36e43be1c62a181f4d7fae20b17a8a21e286c3b1d313b0956592cab71cc62dc7
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef21fbf0f1624eb1291b3abe9e45b7a8520a0eae01c55ae3d01e4eeb9bb96a80
+oid sha256:6170cd0bd2aafac118af3ba9f2edc9e00fcf5d33c6be4bd003b575f8734474b0
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c65509e936785ca3132bf2e751d44c069b4ee0c9b23d6e6dda0e6279496c03fd
+oid sha256:12e99284c5ea2c8361bc41fb3cf40ea6a992d2504f5c1cf2d6e14796ef2eacb6
 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": 0.002675860649410796,
+  "epoch": 0.003430590576167687,
   "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": 0.6961,
       "step": 35
+    },
+    {
+      "epoch": 0.0027444724609341498,
+      "grad_norm": 2.760657548904419,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4957,
+      "step": 40
+    },
+    {
+      "epoch": 0.0027444724609341498,
+      "eval_loss": 0.5292468070983887,
+      "eval_runtime": 789.8718,
+      "eval_samples_per_second": 7.77,
+      "eval_steps_per_second": 3.885,
+      "step": 40
+    },
+    {
+      "epoch": 0.0030875315185509185,
+      "grad_norm": 2.998859167098999,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5017,
+      "step": 45
+    },
+    {
+      "epoch": 0.003430590576167687,
+      "grad_norm": 2.307544469833374,
+      "learning_rate": 0.0,
+      "loss": 0.4898,
+      "step": 50
+    },
+    {
+      "epoch": 0.003430590576167687,
+      "eval_loss": 0.4882238805294037,
+      "eval_runtime": 790.4003,
+      "eval_samples_per_second": 7.764,
+      "eval_steps_per_second": 3.883,
+      "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": 9192405143126016.0,
+  "total_flos": 1.1893491014565888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null