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:d2be6e792ce34b3308915cdc5c42ee775adbf714d92c3ad5146e2cde82cce630
+oid sha256:0123db9566cdbeff0d08a8c1339b9e52fb5ad12e980d3549d361475fdd1b3ff6
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5db301bf2865329d8c2169cf69b75bfa73ef5739f8ead74d742c97bde9c48471
+oid sha256:49e19adb548d239d1ce438071b9c5a00f007ddbd7fa162dbf236089b3fb77890
 size 320194002

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": 0.020942408376963352,
+  "epoch": 0.031413612565445025,
   "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": 5.9627,
       "step": 18
+    },
+    {
+      "epoch": 0.02198952879581152,
+      "grad_norm": 1.5644875764846802,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 5.6048,
+      "step": 21
+    },
+    {
+      "epoch": 0.025130890052356022,
+      "grad_norm": 1.8153458833694458,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.8111,
+      "step": 24
+    },
+    {
+      "epoch": 0.025130890052356022,
+      "eval_loss": 1.4594814777374268,
+      "eval_runtime": 57.4463,
+      "eval_samples_per_second": 7.015,
+      "eval_steps_per_second": 3.516,
+      "step": 24
+    },
+    {
+      "epoch": 0.028272251308900525,
+      "grad_norm": 1.5302882194519043,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 5.9313,
+      "step": 27
+    },
+    {
+      "epoch": 0.031413612565445025,
+      "grad_norm": 1.3925120830535889,
+      "learning_rate": 0.0,
+      "loss": 5.9116,
+      "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": 6534646443540480.0,
+  "total_flos": 9801969665310720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null