Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27577d06b2fc78d094b21e197475b42fb59442a490f65c2ea15509a1bb333b75
+oid sha256:e6900c716c222cbbe6de19d273e00661c1413499d44c44f090515e98d2b67aa1
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05abbc05f7f86787a79bd7730e8881a71acabd246eaa440a9dfabd96c0c9c3ce
+oid sha256:865b9377147c420808d83b86584bc0c18f199cf09b87252dacda3b00d274f1ac
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e504d1ad87718d2a08149d9133473bb0f2cd6f7737a9da36c2a6648b5c301ff0
+oid sha256:6122e1d8df6147677da4f9d7b25fd0e4c715525323b5309e3bda5be943f85945
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.65,
+  "epoch": 0.8333333333333334,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,36 @@
       "eval_samples_per_second": 124.91,
       "eval_steps_per_second": 15.729,
       "step": 30
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.272810935974121,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 4.0775,
+      "step": 40
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 4.024642467498779,
+      "eval_runtime": 3.2316,
+      "eval_samples_per_second": 125.327,
+      "eval_steps_per_second": 15.782,
+      "step": 40
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.1972110271453857,
+      "learning_rate": 0.0,
+      "loss": 3.8715,
+      "step": 50
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "eval_loss": 3.9678239822387695,
+      "eval_runtime": 3.2072,
+      "eval_samples_per_second": 126.279,
+      "eval_steps_per_second": 15.902,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +104,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4279722779344896.0,
+  "total_flos": 5486824076083200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null