Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:343dfb75fb5c0ea331bb2fea28faa4a62f086a7a5d2e36f8ee0ac386ded7fb33
+oid sha256:73c8cd7dd6b773819504a5860eaf636fd34cba23e533397bad4ad66eda966c6d
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ff2227ceb1f5a2ee89106e1c6e1021a48cff57efe25c1149e99d0bec513e79a
+oid sha256:e8486569c6ba98c75320b542aff8de4ee1bb1e4b86194ba2fdffa09c308cca38
 size 102030196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:742ac93365f9f5139042c83640a290eb5bf78fa0571f5209fdc989f29567f644
+oid sha256:aa2fdf332f5e8f9cfebaf6265da7d092beca1eb09578fc271bea99f9a0578edb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9249a82eef8eec6a1c71d7af2159d50f378e28b90f1d4a939b2f9ac7c40432e
+oid sha256:e8eeea5c208aac12ca1d7588ccb40479c9754522c5504911db2e6c3df2af3627
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7933884297520661,
+  "epoch": 1.0578512396694215,
   "eval_steps": 4,
-  "global_step": 12,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -123,6 +123,42 @@
       "eval_samples_per_second": 6.057,
       "eval_steps_per_second": 3.029,
       "step": 12
+    },
+    {
+      "epoch": 0.859504132231405,
+      "grad_norm": 12.169748306274414,
+      "learning_rate": 5e-05,
+      "loss": 3.2708,
+      "step": 13
+    },
+    {
+      "epoch": 0.9256198347107438,
+      "grad_norm": 10.57578182220459,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.9721,
+      "step": 14
+    },
+    {
+      "epoch": 0.9917355371900827,
+      "grad_norm": 7.540788650512695,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.7016,
+      "step": 15
+    },
+    {
+      "epoch": 1.0578512396694215,
+      "grad_norm": 17.30004119873047,
+      "learning_rate": 0.0,
+      "loss": 4.6603,
+      "step": 16
+    },
+    {
+      "epoch": 1.0578512396694215,
+      "eval_loss": 2.5297980308532715,
+      "eval_runtime": 4.3127,
+      "eval_samples_per_second": 6.029,
+      "eval_steps_per_second": 3.014,
+      "step": 16
     }
   ],
   "logging_steps": 1,
@@ -137,12 +173,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.362185870809498e+16,
+  "total_flos": 9.816247827745997e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null