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:b9384b0c003008c18564efaf8289f01d14db89bb5c20b5f8820deed7e05b464e
+oid sha256:5521023b3ddec7b3bb48abc3c6044e5d5495ec94b2c0d996a57225a6a0312af0
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c91889ae4f7129c68b11b8ddc1a112a23fd732243a74cd14b3edaeeaad07b65
+oid sha256:6888ecd327ce4870ed7c7c280645e443dffa4316e8e06395451673a669bb5a03
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bc49e406d40d15d4c77a549f46af25554828e4ccf4a2549a6e443a9a7b138dc
+oid sha256:ac74a516e27937bba2984006840b562b37397862f98eb3e48e06fc76f189dc23
 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": 0.05082592121982211,
+  "epoch": 0.07623888182973317,
   "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": 4.8306,
       "step": 18
+    },
+    {
+      "epoch": 0.053367217280813214,
+      "grad_norm": 0.6494523882865906,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 4.9165,
+      "step": 21
+    },
+    {
+      "epoch": 0.060991105463786534,
+      "grad_norm": 0.6389119625091553,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.0326,
+      "step": 24
+    },
+    {
+      "epoch": 0.060991105463786534,
+      "eval_loss": 4.910366058349609,
+      "eval_runtime": 14.1471,
+      "eval_samples_per_second": 11.734,
+      "eval_steps_per_second": 5.867,
+      "step": 24
+    },
+    {
+      "epoch": 0.06861499364675985,
+      "grad_norm": 0.6531729102134705,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 4.8767,
+      "step": 27
+    },
+    {
+      "epoch": 0.07623888182973317,
+      "grad_norm": 0.5290908813476562,
+      "learning_rate": 0.0,
+      "loss": 4.9477,
+      "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": 7419001684623360.0,
+  "total_flos": 1.112850252693504e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null