Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d5bcdca47329b044066eeb6adc558ff4b9fce8a1746bc09dea5ad3fac999fcb
+oid sha256:0c73e3d66ce90a83bd5f7e8e7bc000ac866184ae7807ad432e002f2ec1a01462
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68d4d2cf15647da729d7356282631d623a7f9836dc5935493ea4f5ecf7288501
+oid sha256:c5771cfd754eed5e6516ec2bb0144fa4e66f4c0fe815900bfadb0374f563a548
 size 320082106

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": 0.00044936246699994384,
+  "epoch": 0.0006740437004999157,
   "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": 1.5926,
       "step": 18
+    },
+    {
+      "epoch": 0.00047183059034994104,
+      "grad_norm": 1.3818286657333374,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.692,
+      "step": 21
+    },
+    {
+      "epoch": 0.0005392349603999326,
+      "grad_norm": 1.7987537384033203,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.5461,
+      "step": 24
+    },
+    {
+      "epoch": 0.0005392349603999326,
+      "eval_loss": 1.6750073432922363,
+      "eval_runtime": 2283.4584,
+      "eval_samples_per_second": 8.207,
+      "eval_steps_per_second": 4.103,
+      "step": 24
+    },
+    {
+      "epoch": 0.0006066393304499242,
+      "grad_norm": 2.41343092918396,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.5868,
+      "step": 27
+    },
+    {
+      "epoch": 0.0006740437004999157,
+      "grad_norm": 1.2482473850250244,
+      "learning_rate": 0.0,
+      "loss": 1.6203,
+      "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": 6610941168844800.0,
+  "total_flos": 9916411753267200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null