Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25046799da9cd14dbf2b191d19c4ea876482fef720612eae380d0e73c1f14370
+oid sha256:0bdc91876f9c16dac5544a3dbdf4ef12dfdf1ceae009a65ac5a1990a116f3c89
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd017759bc63b153d41d240c9a48e649af9c8e9de2a56de116602eee8854954
+oid sha256:92f05d5a090352352445364db0ea7ba38dd5c2af0823aee79608697ce5eecc7d
 size 27002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da212283b2b7a0bbff4ab7ea6ad9a364cde6eea0958471709889adfdc18c077b
+oid sha256:494b33d421b03d1cd28f79b8a14e3ee58ac7b56ac617857ec95c88d4246e6c4f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e67cb47ff12ababb2db5752a0059510ef75c13ebd9ed242d32d1eb2ba8aa08
+oid sha256:204b783eee4578e262211ed4342a25463d72b9f2b43a34a1fb0c83abcbfcca96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01270513499205929,
+  "epoch": 0.019057702488088937,
   "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": 0.0001963525491562421,
       "loss": 138.0,
       "step": 18
+    },
+    {
+      "epoch": 0.013340391741662256,
+      "grad_norm": 3.3322605304419994e-05,
+      "learning_rate": 0.00012653483024396533,
+      "loss": 138.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.015246161990471149,
+      "grad_norm": 4.744883699459024e-05,
+      "learning_rate": 6.183221215612904e-05,
+      "loss": 138.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.015246161990471149,
+      "eval_loss": 11.5,
+      "eval_runtime": 23.755,
+      "eval_samples_per_second": 125.574,
+      "eval_steps_per_second": 41.886,
+      "step": 24
+    },
+    {
+      "epoch": 0.017151932239280042,
+      "grad_norm": 3.736266808118671e-05,
+      "learning_rate": 1.634902137174483e-05,
+      "loss": 138.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.019057702488088937,
+      "grad_norm": 4.924211316392757e-05,
+      "learning_rate": 0.0,
+      "loss": 138.0,
+      "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": 6567893581824.0,
+  "total_flos": 9934126055424.0,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null