Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:872d2bdaf3d9ab95b52edf00722b8ca5b1b526f6f3a765faea06e1721e1c0dc9
+oid sha256:743815b4ae1aa20518087bc63c2b8e24e7638992c39c7c962224af2a39e2db3f
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af71065ca401d7bc02ace1af20cc21b927eb14c9e5e5e276af1cd4afb7e5a706
+oid sha256:9a31da814ed65686a55be7fce7e0f27bee6c972c18497188a310c2b264e81cd6
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1698424ff146bcbfe1356a243484a7bf217ef6a25305200a2a40567c1858ba0
+oid sha256:2e3540149a4da276050c8040279e53fbd6bae2961729657791763596edd20e7b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015594541910331383,
+  "epoch": 0.023391812865497075,
   "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": 17.876,
       "eval_steps_per_second": 8.938,
       "step": 20
+    },
+    {
+      "epoch": 0.016374269005847954,
+      "grad_norm": 1.1809688806533813,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 6.1733,
+      "step": 21
+    },
+    {
+      "epoch": 0.01871345029239766,
+      "grad_norm": 1.011317253112793,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 6.1793,
+      "step": 24
+    },
+    {
+      "epoch": 0.01949317738791423,
+      "eval_loss": 1.5051518678665161,
+      "eval_runtime": 30.2843,
+      "eval_samples_per_second": 17.831,
+      "eval_steps_per_second": 8.916,
+      "step": 25
+    },
+    {
+      "epoch": 0.021052631578947368,
+      "grad_norm": 1.0300302505493164,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 6.5163,
+      "step": 27
+    },
+    {
+      "epoch": 0.023391812865497075,
+      "grad_norm": 1.0304522514343262,
+      "learning_rate": 0.0,
+      "loss": 5.9148,
+      "step": 30
+    },
+    {
+      "epoch": 0.023391812865497075,
+      "eval_loss": 1.503052830696106,
+      "eval_runtime": 30.1741,
+      "eval_samples_per_second": 17.896,
+      "eval_steps_per_second": 8.948,
+      "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": 3684183016734720.0,
+  "total_flos": 5526274525102080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null