Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56c576c1638e3b1995d770b8f4121ac4fdb4a2461eb07636bea6bb28a3394892
+oid sha256:20e7d1cda38825f5f4ab77fec24d721b8849cea249a639da5863ef5162b0b90b
 size 95402480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc4bfdb26716614f6f39962be832db092d363184b6008c166b04b9e7da445605
+oid sha256:30820d4b315181134d481fae53d2857d66475787558aa5cdfdd3ea28e5185617
 size 191012170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ade607607d2e5fd1a7b9c5ede822b5677443b2fded4b4d1eead1130e4103e836
+oid sha256:7f095dd7b2352750be886d7c2eae9998848cc02bf8ab2ad29e5cf29938c032b1
 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": 0.0006163423165225966,
+  "epoch": 0.000924513474783895,
   "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": 11.9407,
       "step": 18
+    },
+    {
+      "epoch": 0.0006471594323487265,
+      "grad_norm": 8.636916160583496,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 12.1578,
+      "step": 21
+    },
+    {
+      "epoch": 0.000739610779827116,
+      "grad_norm": 13.124001502990723,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 12.001,
+      "step": 24
+    },
+    {
+      "epoch": 0.000739610779827116,
+      "eval_loss": 1.9116382598876953,
+      "eval_runtime": 856.1209,
+      "eval_samples_per_second": 15.959,
+      "eval_steps_per_second": 7.98,
+      "step": 24
+    },
+    {
+      "epoch": 0.0008320621273055055,
+      "grad_norm": 7.522345066070557,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 11.3697,
+      "step": 27
+    },
+    {
+      "epoch": 0.000924513474783895,
+      "grad_norm": 13.564047813415527,
+      "learning_rate": 0.0,
+      "loss": 10.8175,
+      "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": 2853976575836160.0,
+  "total_flos": 4316639570952192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null