Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:268efba0d7f2480f26b6132241677d88d9dccc7f4dcbd837dabc0b0702666d68
+oid sha256:b8a4ae092c68c4a972c0bcc432a7066df37a0ba0ceadfcb24bcffe78246d58a3
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dea9a83382fabdab85f30282318536daca02be35a0f1f4a8696e2aa2ddf0f6b
+oid sha256:48d141d45a0bf36c837312b5a4e6b7579dd0942388ec70ca79a29170899f0c35
 size 436251442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44eec565601fef9e0260b681960ec5d77d6b2d3c5820901bf43411292e9beeed
+oid sha256:8cee88312c99b3a12cd850d26334a1bd02b798abda2c992092ce06c3ee963ad3
 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": 0.008506113769271665,
+  "epoch": 0.012759170653907496,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 4.021,
       "eval_steps_per_second": 2.01,
       "step": 20
+    },
+    {
+      "epoch": 0.008931419457735247,
+      "grad_norm": 0.4921725392341614,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.1052,
+      "step": 21
+    },
+    {
+      "epoch": 0.010207336523125997,
+      "grad_norm": 1.406823992729187,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.2115,
+      "step": 24
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "eval_loss": 1.2244946956634521,
+      "eval_runtime": 246.2027,
+      "eval_samples_per_second": 4.021,
+      "eval_steps_per_second": 2.011,
+      "step": 25
+    },
+    {
+      "epoch": 0.011483253588516746,
+      "grad_norm": 0.5751722455024719,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.1404,
+      "step": 27
+    },
+    {
+      "epoch": 0.012759170653907496,
+      "grad_norm": 0.6203330159187317,
+      "learning_rate": 0.0,
+      "loss": 1.2552,
+      "step": 30
+    },
+    {
+      "epoch": 0.012759170653907496,
+      "eval_loss": 1.2219502925872803,
+      "eval_runtime": 246.3094,
+      "eval_samples_per_second": 4.019,
+      "eval_steps_per_second": 2.01,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9534936616796160.0,
+  "total_flos": 1.3878629964447744e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null