Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba5c97c7a7375c1b850cca75fa351a16aa9771d60ee7cf265dd75c24f4ddf75
+oid sha256:6ff1c24f2b3405197194bee8a5878f9609f1cc84a853e6d971b8e019f1f35adf
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e663d1a27b28b4f232ffbf2cd8c9e1625d6550a294dd8bd4b1ff9550f6e4a36d
+oid sha256:777bc0b9623d1c226be02a4ca01a355fe3f4a14c80e37f4375ff6cc83262930c
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec134605e1e781fc705a3279e09b0cbaee66f077da601816e59f2b3169ff7952
+oid sha256:6f242766bba40d78e0edc53cc5807056df7dadda9101747faa82c009ccd450b7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014908684308609765,
+  "epoch": 0.02236302646291465,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 1.6624,
       "step": 18
+    },
+    {
+      "epoch": 0.015654118524040254,
+      "grad_norm": 4.60991907119751,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.2822,
+      "step": 21
+    },
+    {
+      "epoch": 0.017890421170331718,
+      "grad_norm": 2.014559030532837,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.0077,
+      "step": 24
+    },
+    {
+      "epoch": 0.017890421170331718,
+      "eval_loss": 1.0028789043426514,
+      "eval_runtime": 5.6501,
+      "eval_samples_per_second": 99.998,
+      "eval_steps_per_second": 50.088,
+      "step": 24
+    },
+    {
+      "epoch": 0.02012672381662318,
+      "grad_norm": 2.1602630615234375,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.9325,
+      "step": 27
+    },
+    {
+      "epoch": 0.02236302646291465,
+      "grad_norm": 2.1503665447235107,
+      "learning_rate": 0.0,
+      "loss": 0.8752,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 138837586083840.0,
+  "total_flos": 208256379125760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null